Showing 1–50 of 50 results for author: Bakker, M

Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce

Authors: Zeyuan Li, Lukas Petersson, Alessandro Acquisti, Michiel A. Bakker

Abstract: Frontier LLM agents increasingly transact on behalf of separate principals, often using natural language rather than structured APIs. Much of the safety literature studies misaligned LLM behavior through adversarial-elicitation evaluations on single agents or stylized tasks. Its prevalence and structure in settings that combine long horizons, separate principals, real operational state, and inter-… ▽ More Frontier LLM agents increasingly transact on behalf of separate principals, often using natural language rather than structured APIs. Much of the safety literature studies misaligned LLM behavior through adversarial-elicitation evaluations on single agents or stylized tasks. Its prevalence and structure in settings that combine long horizons, separate principals, real operational state, and inter-agent natural-language exchange remain insufficiently measured. We study 2,583 inter-agent emails from 20 one-year simulation runs of Vending-Bench Arena, a competitive vending environment spanning 13 frontier LLMs. We operationalize speech-act misalignment as emails containing false factual claims, manipulation, collusion, or threats, combining message content with ground-truth simulator state and logged reasoning traces to classify and validate such behavior. Under our primary classifier, 12.6% of emails are labeled misaligned; misalignment appears in all 20 runs and 74.7% of individual agent-runs. Both the magnitude and composition of this misalignment are preserved under repeated classification at different sampling temperatures and under full-pipeline replication with judges from two other frontier-model families. Misalignment is also reciprocal and stress-conditioned: receiving a misaligned email from a counterparty raises the odds of a misaligned reply by 1.65x, and low-inventory conditions raise them by 1.58x. Across tests of capability-asymmetric exploitation, we find no evidence that higher-capability models differentially exploit weaker counterparties, and model performance rank does not predict misalignment rates. Together, these results indicate that measurable, state-dependent misalignment can arise in competitive multi-agent environments without engineered elicitation, in patterns associated with operational scarcity and counterparty behavior rather than model capability alone. △ Less

Submitted 17 August, 2026; v1 submitted 14 August, 2026; originally announced August 2026.

A Roadmap to Impactful Pluralistic Alignment Research

Authors: Elinor Poole-Dayan, Jillian Fisher, Atoosa Kasirzadeh, Jacob Andreas, Mitchell Gordon, Michiel A. Bakker

Abstract: Pluralistic value alignment---the goal of building AI systems that represent and serve diverse human values and perspectives---has emerged as an active research agenda. Yet, there's no public evidence that it has shaped the training or evaluation of the AI systems people actually use. We audit the public behavior documents and evaluations of frontier labs, finding none name pluralism as a goal, an… ▽ More Pluralistic value alignment---the goal of building AI systems that represent and serve diverse human values and perspectives---has emerged as an active research agenda. Yet, there's no public evidence that it has shaped the training or evaluation of the AI systems people actually use. We audit the public behavior documents and evaluations of frontier labs, finding none name pluralism as a goal, and as of this writing, no clear indication that production models are explicitly trained or tested for it. This goes against the primary motivations and goals of pluralistic alignment, which revolve around making a positive difference in the models serving billions of users worldwide. We argue that the pluralistic alignment research community should focus on supporting impact and adoption in deployed, widely-used AI systems. We provide evidence for the adoption problem, present three main reasons behind it, and discuss three corresponding areas for future research to address it: 1. The primary justifications for pluralistic alignment so far have been normative or speculative. We need studies showing empirically how pluralistic AI benefits users or society. 2. The pluralistic alignment research community has not settled when pluralistic behavior is warranted or what pluralism ideally looks like in practice. We need to establish a concrete goal for developers to operationalize. 3. Current methods trade off against other desiderata of LLMs in ways that are largely unmeasured, and existing metrics are not "hill-climbable." We need trade-off-aware evaluations and methods that meet the requirements of production systems. This paper serves as a collective call to action for the pluralistic alignment researchers: progress requires moving beyond normative justification toward empirical foundations, a concrete account of ideal pluralistic behavior, and practical methods and evaluations built for adoption. △ Less

Submitted 24 July, 2026; originally announced July 2026.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems

Authors: Xiaoyang Cao, Siddarth Srinivasan, Michiel A. Bakker

Abstract: End-to-end reinforcement learning can improve the accuracy of compound LLM systems, but it does not constrain how modules divide labor internally. We identify Role Drift, a failure mode in which modules preserve or improve end-task performance while deviating from their assigned roles through role-violating shortcuts that remain invisible to system-level evaluation. To make role drift observable a… ▽ More End-to-end reinforcement learning can improve the accuracy of compound LLM systems, but it does not constrain how modules divide labor internally. We identify Role Drift, a failure mode in which modules preserve or improve end-task performance while deviating from their assigned roles through role-violating shortcuts that remain invisible to system-level evaluation. To make role drift observable and controllable, we propose Role Anchor, a regularizer that modulates how much each module deviates from its assigned role during end-to-end training. The key idea is to preserve how the role prompt shifts the module's next-token predictions relative to a neutral prompt, which serves as a proxy for the role's intended effect during training. Experiments on two compound LLM pipelines reveal role drift that accuracy alone fails to detect: a decomposer meant to split a question into sub-questions for a separate solver instead plants the answer in them, and a reader meant to answer from retrieved passages instead falls back on parametric memory. In fact, on the decomposer pipeline this shortcut drives most of the apparent RL gain: 86% of it vanishes once the decomposer is held to its role, indicating that terminal accuracy alone can badly overstate how much a compound system has genuinely learned. Across both pipelines, Role Anchor mitigates role drift at a tunable accuracy cost that varies by pipeline and anchor strength. Additional gradient analysis suggests that the regularizer reduces alignment with the role-drift direction rather than simply suppressing learning. △ Less

Submitted 7 July, 2026; originally announced July 2026.

Habermolt: Delegating Deliberation to AI Representatives

Authors: Joseph Low, Oscar Duys, Claude Formanek, Michiel Bakker, Lewis Hammond

Abstract: Deliberative democracy arguably leads to better collective decisions, but is fundamentally constrained by human attention and bandwidth. While recent AI-mediated deliberations scale participation by synthesizing inputs from many humans, they remain time-intensive for individual users. As AI models become increasingly capable, AI systems are being deployed not only to mediate deliberation between h… ▽ More Deliberative democracy arguably leads to better collective decisions, but is fundamentally constrained by human attention and bandwidth. While recent AI-mediated deliberations scale participation by synthesizing inputs from many humans, they remain time-intensive for individual users. As AI models become increasingly capable, AI systems are being deployed not only to mediate deliberation between humans, but to represent humans in it: where AI agents deliberate on behalf of human users. We call this paradigm AI-delegated deliberation. While it promises unprecedented scale for democratic participation, it introduces qualitatively new design and alignment challenges that are poorly understood and under-theorized. To study these dynamics empirically, we deploy Habermolt, a public platform for AI-delegated deliberation. We evaluate its effectiveness along three dimensions that we use to organize any deliberative system: representation, aggregation, and revision. We use these observations to illuminate the design decisions future AI-delegated deliberation platforms must confront, contributing to the broader research agenda for scalable yet trustworthy AI representatives. △ Less

Submitted 27 May, 2026; v1 submitted 23 May, 2026; originally announced May 2026.

Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation

Authors: Joshua C. Yang, Maurice Flechtner, Damian Dailisan, Michiel A. Bakker

Abstract: LLM-based agents are increasingly used to simulate deliberative interactions such as negotiation, conflict resolution, and multi-turn opinion exchange. Yet generated transcripts often do not reveal why an agent's stance changes: movement may reflect evidence uptake, anchoring, role drift, echoing, or changed prompt and retrieval context. We introduce the Belief Engine (BE), an auditable belief-upd… ▽ More LLM-based agents are increasingly used to simulate deliberative interactions such as negotiation, conflict resolution, and multi-turn opinion exchange. Yet generated transcripts often do not reveal why an agent's stance changes: movement may reflect evidence uptake, anchoring, role drift, echoing, or changed prompt and retrieval context. We introduce the Belief Engine (BE), an auditable belief-update layer that treats "belief" as an evidential state over a proposition and exposes it as scalar stance. BE extracts arguments into structured memory and updates stance with a log-odds rule controlled by evidence uptake u and prior anchoring a. Across multiple base LLMs, parameter sweeps show that these controls reliably shape stance dynamics while preserving an evidence-level update trail. On DEBATE, a human deliberation dataset with pre/post opinions, BE best reconstructs participants whose final stance follows extracted evidence; stable and evidence-opposed cases instead point to anchoring or factors outside the extracted evidence stream. BE provides configurable infrastructure for studying evidence-grounded deliberation, where openness, commitment, convergence, and disagreement can be tied to explicit update assumptions rather than hidden prompt effects. △ Less

Submitted 14 May, 2026; originally announced May 2026.

Europe and the Geopolitics of AGI: The Need for a Preparedness Plan

Authors: Maximilian Negele, Daan Juijn, Afek Shamir, David Janků, Bengüsu Özcan, Lisa Soder, Lucia Velasco, Max Reddel, Michiel Bakker, Lorenzo Pacchiardi, Maksym Andriushchenko

Abstract: Artificial general intelligence (AGI)--defined here as AI systems that match or exceed humans at most economically useful cognitive work--has moved from speculation to the centre of political and strategic debate. This paper examines three questions: how soon AGI might emerge, how it could reshape geopolitics, and whether Europe is adequately prepared. Drawing on empirical trends in AI capabilitie… ▽ More Artificial general intelligence (AGI)--defined here as AI systems that match or exceed humans at most economically useful cognitive work--has moved from speculation to the centre of political and strategic debate. This paper examines three questions: how soon AGI might emerge, how it could reshape geopolitics, and whether Europe is adequately prepared. Drawing on empirical trends in AI capabilities, expert forecasting surveys, and policy analysis, we find that a plausible window for AGI emergence falls between 2030 and 2040, or potentially earlier, though substantial uncertainty remains. Our analysis of the geopolitical implications suggests that AGI could fundamentally alter the global distribution of economic and military power, intensify interstate competition, and strain existing governance frameworks. Assessing Europe's current positioning, we identify critical gaps: limited strategic awareness of frontier AI progress, structural weaknesses in compute infrastructure and talent retention, low rates of industrial AI adoption, and fragmented policy responses at both EU and Member State levels that do not match the potential scale of disruption.These findings point to a need for a coordinated European preparedness agenda. We outline policy options centred on building institutional capacity for AGI situational awareness, strengthening Europe's position in the AI value chain, and developing frameworks for international stability in an era of increasingly capable AI systems. △ Less

Submitted 13 May, 2026; originally announced May 2026.

Comments: 84 pages, 12 figures

Report number: RR-A4636-1

Multi-User Large Language Model Agents

Authors: Shu Yang, Shenzhe Zhu, Hao Zhu, José Ramón Enríquez, Di Wang, Alex Pentland, Michiel A. Bakker, Jiaxin Pei

Abstract: Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are implicitly optimized for a single-principal interaction paradigm, in which the model is designed to satisfy the objectives of one dominant user whose instructions are treated as the sole source of authority and utility. However, as they are integr… ▽ More Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are implicitly optimized for a single-principal interaction paradigm, in which the model is designed to satisfy the objectives of one dominant user whose instructions are treated as the sole source of authority and utility. However, as they are integrated into team workflows and organizational tools, they are increasingly required to serve multiple users simultaneously, each with distinct roles, preferences, and authority levels, leading to multi-user, multi-principal settings with unavoidable conflicts, information asymmetry, and privacy constraints. In this work, we present the first systematic study of multi-user LLM agents. We begin by formalizing multi-user interaction with LLM agents as a multi-principal decision problem, where a single agent must account for multiple users with potentially conflicting interests and associated challenges. We then introduce a unified multi-user interaction protocol and design three targeted stress-testing scenarios to evaluate current LLMs' capabilities in instruction following, privacy preservation, and coordination. Our results reveal systematic gaps: frontier LLMs frequently fail to maintain stable prioritization under conflicting user objectives, exhibit increasing privacy violations over multi-turn interactions, and suffer from efficiency bottlenecks when coordination requires iterative information gathering. △ Less

Submitted 27 April, 2026; v1 submitted 19 March, 2026; originally announced April 2026.

AI and Collective Decisions: Strengthening Legitimacy and Losers' Consent

Authors: Suyash Fulay, Prerna Ravi, Emily Kubin, Shrestha Mohanty, Michiel Bakker, Deb Roy

Abstract: AI is increasingly used to scale collective decision-making, but far less attention has been paid to how such systems can support procedural legitimacy, particularly the conditions shaping losers' consent: whether participants who do not get their preferred outcome still accept it as fair. We ask: (1) how can AI help ground collective decisions in participants' different experiences and beliefs, a… ▽ More AI is increasingly used to scale collective decision-making, but far less attention has been paid to how such systems can support procedural legitimacy, particularly the conditions shaping losers' consent: whether participants who do not get their preferred outcome still accept it as fair. We ask: (1) how can AI help ground collective decisions in participants' different experiences and beliefs, and (2) whether exposure to these experiences can increase trust, understanding, and social cohesion even when people disagree with the outcome. We built a system that uses a semi-structured AI interviewer to elicit personal experiences on policy topics and an interactive visualization that displays predicted policy support alongside those voiced experiences. In a randomized experiment (n = 181), interacting with the visualization increased perceived legitimacy, trust in outcomes, and understanding of others' perspectives, even though all participants encountered decisions that went against their stated preferences. Our hope is that the design and evaluation of this tool spurs future researchers to focus on how AI can help not only achieve scale and efficiency in democratic processes, but also increase trust and connection between participants. △ Less

Submitted 6 April, 2026; originally announced April 2026.

Comments: 11 pages + appendix

AI Assistance Reduces Persistence and Hurts Independent Performance

Authors: Grace Liu, Brian Christian, Tsvetomira Dumbalska, Michiel A. Bakker, Rachit Dubey

Abstract: People often optimize for long-term goals in collaboration: A mentor or companion doesn't just answer questions, but also scaffolds learning, tracks progress, and prioritizes the other person's growth over immediate results. In contrast, current AI systems are fundamentally short-sighted collaborators - optimized for providing instant and complete responses, without ever saying no (unless for safe… ▽ More People often optimize for long-term goals in collaboration: A mentor or companion doesn't just answer questions, but also scaffolds learning, tracks progress, and prioritizes the other person's growth over immediate results. In contrast, current AI systems are fundamentally short-sighted collaborators - optimized for providing instant and complete responses, without ever saying no (unless for safety reasons). What are the consequences of this dynamic? Here, through a series of randomized controlled trials on human-AI interactions (N = 1,222), we provide causal evidence for two key consequences of AI assistance: reduced persistence and impairment of unassisted performance. Across a variety of tasks, including mathematical reasoning and reading comprehension, we find that although AI assistance improves performance in the short-term, people perform significantly worse without AI and are more likely to give up. Notably, these effects emerge after only brief interactions with AI (approximately 10 minutes). These findings are particularly concerning because persistence is foundational to skill acquisition and is one of the strongest predictors of long-term learning. We posit that persistence is reduced because AI conditions people to expect immediate answers, thereby denying them the experience of working through challenges on their own. These results suggest the need for AI model development to prioritize scaffolding long-term competence alongside immediate task completion. △ Less

Submitted 5 August, 2026; v1 submitted 6 April, 2026; originally announced April 2026.

AI Fact-Checking in the Wild: A Field Evaluation of LLM-Written Community Notes on X

Authors: Haiwen Li, Michiel A. Bakker

Abstract: Large language models (LLMs) show promising capabilities for fact-checking, yet prior work evaluates them only in controlled offline settings using benchmarks or crowdworker judgments. Success in real-world fact-checking depends also on how content is judged within a live platform environment. We present the first field evaluation of LLM fact-checking deployed on a live social media platform, test… ▽ More Large language models (LLMs) show promising capabilities for fact-checking, yet prior work evaluates them only in controlled offline settings using benchmarks or crowdworker judgments. Success in real-world fact-checking depends also on how content is judged within a live platform environment. We present the first field evaluation of LLM fact-checking deployed on a live social media platform, testing performance directly through X Community Notes' "AI writer" feature over a three-month period. Our LLM writer, a multi-step pipeline that handles multimodal content, conducts web and platform-native search, and writes contextual notes, was deployed to write 1,614 notes on 1,597 tweets and compared against 1,332 human-written notes on the same tweets using 108,169 ratings from 42,521 raters. Direct comparison of note-level platform outcomes is complicated by differences in submission timing and exposure between LLM and human notes; we therefore pursue two analysis strategies: a rating-level analysis modeling individual rater evaluations, and a note-level analysis that relies on common raters who rated all notes on the same post. Rating-level analysis shows that LLM notes receive more positive ratings than human notes across raters with different political viewpoints, and note-level analysis shows LLM notes achieve significantly higher helpfulness scores among common raters. Rater-provided tags suggest that people consider LLM notes to use more neutral language and cite better sources. These findings provide field evidence that LLMs can contribute broadly helpful fact-checking notes at scale, while showing that their evaluation is shaped by platform dynamics absent from controlled offline settings. △ Less

Submitted 18 August, 2026; v1 submitted 2 April, 2026; originally announced April 2026.

Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift

Authors: Michelle Vaccaro, Jaeyoon Song, Abdullah Almaatouq, Michiel A. Bakker

Abstract: Current frontier AI safety evaluations emphasize static benchmarks, third-party annotations, and red-teaming. In this position paper, we argue that AI safety research should focus on human-centered evaluations that measure harmful capability uplift: the marginal increase in a user's ability to cause harm with a frontier model beyond what conventional tools already enable. We frame harmful capabili… ▽ More Current frontier AI safety evaluations emphasize static benchmarks, third-party annotations, and red-teaming. In this position paper, we argue that AI safety research should focus on human-centered evaluations that measure harmful capability uplift: the marginal increase in a user's ability to cause harm with a frontier model beyond what conventional tools already enable. We frame harmful capability uplift as a core AI safety metric, ground it in prior social science research, and provide concrete methodological guidance for systematic measurement. We conclude with actionable steps for developers, researchers, funders, and regulators to make harmful capability uplift evaluation a standard practice. △ Less

Submitted 6 March, 2026; originally announced March 2026.

Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice

Authors: Prerna Ravi, Om Gokhale, Suyash Fulay, Eugene Yi, Deb Roy, Michiel Bakker

Abstract: Deliberative democratic theory suggests that civic competence: the capacity to navigate disagreement, weigh competing values, and arrive at collective decisions is not innate but developed through practice. Yet opportunities to cultivate these skills remain limited, as traditional deliberative processes like citizens' assemblies reach only a small fraction of the population. We present Agora, an A… ▽ More Deliberative democratic theory suggests that civic competence: the capacity to navigate disagreement, weigh competing values, and arrive at collective decisions is not innate but developed through practice. Yet opportunities to cultivate these skills remain limited, as traditional deliberative processes like citizens' assemblies reach only a small fraction of the population. We present Agora, an AI-powered platform that uses LLMs to organize authentic human voices on policy issues, helping users build consensus-finding skills by proposing and revising policy recommendations, hearing supporting and opposing perspectives, and receiving feedback on how policy changes affect predicted support. In a preliminary study with 44 university students, access to the full interface with voice explanations, as opposed to aggregate support distributions alone, significantly improved self-reported perspective-taking and the extent to which statements acknowledged multiple viewpoints. These findings point toward a promising direction for scaling civic education. △ Less

Submitted 6 April, 2026; v1 submitted 7 March, 2026; originally announced March 2026.

Comments: Short version: Accepted to ACM CHI Extended Abstracts 2026 (https://doi.org/10.1145/3772363.3798888); Long version under review

Can AI mediation improve democratic deliberation?

Authors: Michael Henry Tessler, Georgina Evans, Michiel A. Bakker, Iason Gabriel, Sophie Bridgers, Rishub Jain, Raphael Koster, Verena Rieser, Anca Dragan, Matthew Botvinick, Christopher Summerfield

Abstract: The strength of democracy lies in the free and equal exchange of diverse viewpoints. Living up to this ideal at scale faces inherent tensions: broad participation, meaningful deliberation, and political equality often trade off with one another (Fishkin, 2011). We ask whether and how artificial intelligence (AI) could help navigate this "trilemma" by engaging with a recent example of a large langu… ▽ More The strength of democracy lies in the free and equal exchange of diverse viewpoints. Living up to this ideal at scale faces inherent tensions: broad participation, meaningful deliberation, and political equality often trade off with one another (Fishkin, 2011). We ask whether and how artificial intelligence (AI) could help navigate this "trilemma" by engaging with a recent example of a large language model (LLM)-based system designed to help people with diverse viewpoints find common ground (Tessler, Bakker, et al., 2024). Here, we explore the implications of the introduction of LLMs into deliberation augmentation tools, examining their potential to enhance participation through scalability, improve political equality via fair mediation, and foster meaningful deliberation by, for example, surfacing trustworthy information. We also point to key challenges that remain. Ultimately, a range of empirical, technical, and theoretical advancements are needed to fully realize the promise of AI-mediated deliberation for enhancing citizen engagement and strengthening democratic deliberation. △ Less

Submitted 9 January, 2026; originally announced January 2026.

Journal ref: Knight Institute for the First Amendment at Columbia University Symposium on "AI and Democratic Freedoms", April 10-11, 2025

Ontology Learning with LLMs: A Benchmark Study on Axiom Identification

Authors: Roos M. Bakker, Daan L. Di Scala, Maaike H. T. de Boer, Stephan A. Raaijmakers

Abstract: Ontologies are an important tool for structuring domain knowledge, but their development is a complex task that requires significant modelling and domain expertise. Ontology learning, aimed at automating this process, has seen advancements in the past decade with the improvement of Natural Language Processing techniques, and especially with the recent growth of Large Language Models (LLMs). This p… ▽ More Ontologies are an important tool for structuring domain knowledge, but their development is a complex task that requires significant modelling and domain expertise. Ontology learning, aimed at automating this process, has seen advancements in the past decade with the improvement of Natural Language Processing techniques, and especially with the recent growth of Large Language Models (LLMs). This paper investigates the challenge of identifying axioms: fundamental ontology components that define logical relations between classes and properties. In this work, we introduce an Ontology Axiom Benchmark OntoAxiom, and systematically test LLMs on that benchmark for axiom identification, evaluating different prompting strategies, ontologies, and axiom types. The benchmark consists of nine medium-sized ontologies with together 17.118 triples, and 2.771 axioms. We focus on subclass, disjoint, subproperty, domain, and range axioms. To evaluate LLM performance, we compare twelve LLMs with three shot settings and two prompting strategies: a Direct approach where we query all axioms at once, versus an Axiom-by-Axiom (AbA) approach, where each prompt queries for one axiom only. Our findings show that the AbA prompting leads to higher F1 scores than the direct approach. However, performance varies across axioms, suggesting that certain axioms are more challenging to identify. The domain also influences performance: the FOAF ontology achieves a score of 0.642 for the subclass axiom, while the music ontology reaches only 0.218. Larger LLMs outperform smaller ones, but smaller models may still be viable for resource-constrained settings. Although performance overall is not high enough to fully automate axiom identification, LLMs can provide valuable candidate axioms to support ontology engineers with the development and refinement of ontologies. △ Less

Submitted 5 December, 2025; originally announced December 2025.

Comments: Submitted to Semantic Web Journal, under review

MSC Class: 68T30 ACM Class: I.2.4; I.2.7

Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value

Authors: Joe Edelman, Tan Zhi-Xuan, Ryan Lowe, Oliver Klingefjord, Vincent Wang-Mascianica, Matija Franklin, Ryan Othniel Kearns, Ellie Hain, Atrisha Sarkar, Michiel Bakker, Fazl Barez, David Duvenaud, Jakob Foerster, Iason Gabriel, Joseph Gubbels, Bryce Goodman, Andreas Haupt, Jobst Heitzig, Julian Jara-Ettinger, Atoosa Kasirzadeh, James Ravi Kirkpatrick, Andrew Koh, W. Bradley Knox, Philipp Koralus, Joel Lehman , et al. (8 additional authors not shown)

Abstract: Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad outcomes if the goals of that organization are misaligned with those of other institutions and individuals. For this reason, we need full-stack alignment, the… ▽ More Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad outcomes if the goals of that organization are misaligned with those of other institutions and individuals. For this reason, we need full-stack alignment, the concurrent alignment of AI systems and the institutions that shape them with what people value. This can be done without imposing a particular vision of individual or collective flourishing. We argue that current approaches for representing values, such as utility functions, preference orderings, or unstructured text, struggle to address these and other issues effectively. They struggle to distinguish values from other signals, to support principled normative reasoning, and to model collective goods. We propose thick models of value will be needed. These structure the way values and norms are represented, enabling systems to distinguish enduring values from fleeting preferences, to model the social embedding of individual choices, and to reason normatively, applying values in new domains. We demonstrate this approach in five areas: AI value stewardship, normatively competent agents, win-win negotiation systems, meaning-preserving economic mechanisms, and democratic regulatory institutions. △ Less

Submitted 2 December, 2025; originally announced December 2025.

Benchmarking Overton Pluralism in LLMs

Authors: Elinor Poole-Dayan, Jiayi Wu, Taylor Sorensen, Jiaxin Pei, Michiel A. Bakker

Abstract: We introduce OVERTONBENCH, a novel framework for measuring Overton pluralism in LLMs--the extent to which diverse viewpoints are represented in model outputs. We (i) formalize Overton pluralism as a set coverage metric (OVERTONSCORE), (ii) conduct a large-scale U.S.-representative human study (N = 1208; 60 questions; 8 LLMs), and (iii) develop an automated benchmark that closely reproduces human j… ▽ More We introduce OVERTONBENCH, a novel framework for measuring Overton pluralism in LLMs--the extent to which diverse viewpoints are represented in model outputs. We (i) formalize Overton pluralism as a set coverage metric (OVERTONSCORE), (ii) conduct a large-scale U.S.-representative human study (N = 1208; 60 questions; 8 LLMs), and (iii) develop an automated benchmark that closely reproduces human judgments. On average, models achieve OVERTONSCOREs of 0.35--0.41, with DeepSeek V3 performing best; yet all models remain far below the theoretical maximum of 1.0, revealing substantial headroom for improvement. Because repeated large-scale human studies are costly and slow, scalable evaluation tools are essential for model development. Hence, we propose an automated benchmark that achieves high rank correlation with human judgments ($ρ= 0.88$), providing a practical proxy without replacing human assessment. By turning pluralistic alignment from a normative aim into a measurable benchmark, our work establishes a foundation for systematic progress toward more pluralistic LLMs. △ Less

Submitted 2 March, 2026; v1 submitted 1 December, 2025; originally announced December 2025.

Comments: Paper accepted to ICLR 2026

Shareholder Democracy with AI Representatives

Authors: Suyash Fulay, Sercan Demir, Galen Hines-Pierce, Hélène Landemore, Michiel Bakker

Abstract: A large share of retail investors hold public equities through mutual funds, yet lack adequate control over these investments. Indeed, mutual funds concentrate voting power in the hands of a few asset managers. These managers vote on behalf of shareholders despite having limited insight into their individual preferences, leaving them exposed to growing political and regulatory pressures, particula… ▽ More A large share of retail investors hold public equities through mutual funds, yet lack adequate control over these investments. Indeed, mutual funds concentrate voting power in the hands of a few asset managers. These managers vote on behalf of shareholders despite having limited insight into their individual preferences, leaving them exposed to growing political and regulatory pressures, particularly amid rising shareholder activism. Pass-through voting has been proposed as a way to empower retail investors and provide asset managers with clearer guidance, but it faces challenges such as low participation rates and the difficulty of capturing highly individualized shareholder preferences for each specific vote. Randomly selected assemblies of shareholders, or ``investor assemblies,'' have also been proposed as more representative proxies than asset managers. As a third alternative, we propose artificial intelligence (AI) enabled representatives trained on individual shareholder preferences to act as proxies and vote on their behalf. Over time, these models could not only predict how retail investors would vote at any given moment but also how they might vote if they had significantly more time, knowledge, and resources to evaluate each proposal, leading to better overall decision-making. We argue that shareholder democracy offers a compelling real-world test bed for AI-enabled representation, providing valuable insights into both the potential benefits and risks of this approach more generally. △ Less

Submitted 27 October, 2025; originally announced October 2025.

From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM

Authors: Suyash Fulay, Jocelyn Zhu, Michiel Bakker

Abstract: Large language models (LLMs) have shown promising accuracy in predicting survey responses and policy preferences, which has increased interest in their potential to represent human interests in various domains. Most existing research has focused on "behavioral cloning", effectively evaluating how well models reproduce individuals' expressed preferences. Drawing on theories of political representat… ▽ More Large language models (LLMs) have shown promising accuracy in predicting survey responses and policy preferences, which has increased interest in their potential to represent human interests in various domains. Most existing research has focused on "behavioral cloning", effectively evaluating how well models reproduce individuals' expressed preferences. Drawing on theories of political representation, we highlight an underexplored design trade-off: whether AI systems should act as delegates, mirroring expressed preferences, or as trustees, exercising judgment about what best serves an individual's interests. This trade-off is closely related to issues of LLM sycophancy, where models can encourage behavior or validate beliefs that may be aligned with a user's short-term preferences, but is detrimental to their long-term interests. Through a series of experiments simulating votes on various policy issues in the U.S. context, we apply a temporal utility framework that weighs short and long-term interests (simulating a trustee role) and compare voting outcomes to behavior-cloning models (simulating a delegate). We find that trustee-style predictions weighted toward long-term interests produce policy decisions that align more closely with expert consensus on well-understood issues, but also show greater bias toward models' default stances on topics lacking clear agreement. These findings reveal a fundamental trade-off in designing AI systems to represent human interests. Delegate models better preserve user autonomy but may diverge from well-supported policy positions, while trustee models can promote welfare on well-understood issues yet risk paternalism and bias on subjective topics. △ Less

Submitted 16 November, 2025; v1 submitted 14 October, 2025; originally announced October 2025.

Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs

Authors: Shenzhe Zhu, Shu Yang, Michiel A. Bakker, Alex Pentland, Jiaxin Pei

Abstract: Large-scale public deliberations generate thousands of free-form contributions that must be synthesized into representative and neutral summaries for policy use. While LLMs have been shown as a promising tool to generate summaries for large-scale deliberations, they also risk underrepresenting minority perspectives and exhibiting bias with respect to the input order, raising fairness concerns in h… ▽ More Large-scale public deliberations generate thousands of free-form contributions that must be synthesized into representative and neutral summaries for policy use. While LLMs have been shown as a promising tool to generate summaries for large-scale deliberations, they also risk underrepresenting minority perspectives and exhibiting bias with respect to the input order, raising fairness concerns in high-stakes contexts. Studying and fixing these issues requires a comprehensive evaluation at a large scale, yet current practice often relies on LLMs as judges, which show weak alignment with human judgments. To address this, we present DeliberationBank, a large-scale human-grounded dataset with (1) opinion data spanning ten deliberation questions created by 3,000 participants and (2) summary judgment data annotated by 4,500 participants across four dimensions (representativeness, informativeness, neutrality, policy approval). Using these datasets, we train DeliberationJudge, a fine-tuned DeBERTa model that can rate deliberation summaries from individual perspectives. DeliberationJudge is more efficient and more aligned with human judgements compared to a wide range of LLM judges. With DeliberationJudge, we evaluate 18 LLMs and reveal persistent weaknesses in deliberation summarization, especially underrepresentation of minority positions. Our framework provides a scalable and reliable way to evaluate deliberation summarization, helping ensure AI systems are more representative and equitable for policymaking. △ Less

Submitted 19 March, 2026; v1 submitted 2 October, 2025; originally announced October 2025.

RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment

Authors: Xiaoyang Cao, Zelai Xu, Mo Guang, Kaiwen Long, Michiel A. Bakker, Yu Wang, Chao Yu

Abstract: Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that preference data is clean and that all labels are equally reliable. In practice, large-scale preference datasets contain substantial noise due to annotator mistakes, i… ▽ More Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that preference data is clean and that all labels are equally reliable. In practice, large-scale preference datasets contain substantial noise due to annotator mistakes, inconsistent instructions, varying expertise, and even adversarial or low-effort feedback. This mismatch between recorded labels and ground-truth preferences can misguide training and degrade model performance. To address this issue, we introduce Robust Enhanced Policy Optimization (RE-PO), which uses an expectation-maximization procedure to infer the posterior correctness of each label and then adaptively reweight data points in the training loss to mitigate label noise. We further generalize this idea by establishing a theoretical link between arbitrary preference losses and their underlying probabilistic models, enabling a systematic transformation of existing alignment algorithms into robust counterparts and elevating RE-PO from a single method to a general framework for robust preference alignment. Theoretically, we prove that, under a perfectly calibrated model, RE-PO recovers the true noise level of the dataset. Empirically, we show that RE-PO consistently improves four state-of-the-art alignment methods (DPO, IPO, SimPO, and CPO); when applied to Mistral and Llama 3 models, the RE-PO-enhanced variants increase AlpacaEval 2 win rates by up to 7.0 percent over their respective baselines. △ Less

Submitted 27 February, 2026; v1 submitted 28 September, 2025; originally announced September 2025.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Authors: Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu , et al. (3410 additional authors not shown)

Abstract: In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal unde… ▽ More In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving. △ Less

Submitted 19 December, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: 72 pages, 17 figures

Scaling Human Judgment in Community Notes with LLMs

Authors: Haiwen Li, Soham De, Manon Revel, Andreas Haupt, Brad Miller, Keith Coleman, Jay Baxter, Martin Saveski, Michiel A. Bakker

Abstract: This paper argues for a new paradigm for Community Notes in the LLM era: an open ecosystem where both humans and LLMs can write notes, and the decision of which notes are helpful enough to show remains in the hands of humans. This approach can accelerate the delivery of notes, while maintaining trust and legitimacy through Community Notes' foundational principle: A community of diverse human rater… ▽ More This paper argues for a new paradigm for Community Notes in the LLM era: an open ecosystem where both humans and LLMs can write notes, and the decision of which notes are helpful enough to show remains in the hands of humans. This approach can accelerate the delivery of notes, while maintaining trust and legitimacy through Community Notes' foundational principle: A community of diverse human raters collectively serve as the ultimate evaluator and arbiter of what is helpful. Further, the feedback from this diverse community can be used to improve LLMs' ability to produce accurate, unbiased, broadly helpful notes--what we term Reinforcement Learning from Community Feedback (RLCF). This becomes a two-way street: LLMs serve as an asset to humans--helping deliver context quickly and with minimal effort--while human feedback, in turn, enhances the performance of LLMs. This paper describes how such a system can work, its benefits, key new risks and challenges it introduces, and a research agenda to solve those challenges and realize the potential of this approach. △ Less

Submitted 30 June, 2025; originally announced June 2025.

Community Moderation and the New Epistemology of Fact Checking on Social Media

Authors: Isabelle Augenstein, Michiel Bakker, Tanmoy Chakraborty, David Corney, Emilio Ferrara, Iryna Gurevych, Scott Hale, Eduard Hovy, Heng Ji, Irene Larraz, Filippo Menczer, Preslav Nakov, Paolo Papotti, Dhruv Sahnan, Greta Warren, Giovanni Zagni

Abstract: Social media platforms have traditionally relied on internal moderation teams and partnerships with independent fact-checking organizations to identify and flag misleading content. Recently, however, platforms including X (formerly Twitter) and Meta have shifted towards community-driven content moderation by launching their own versions of crowd-sourced fact-checking -- Community Notes. If effecti… ▽ More Social media platforms have traditionally relied on internal moderation teams and partnerships with independent fact-checking organizations to identify and flag misleading content. Recently, however, platforms including X (formerly Twitter) and Meta have shifted towards community-driven content moderation by launching their own versions of crowd-sourced fact-checking -- Community Notes. If effectively scaled and governed, such crowd-checking initiatives have the potential to combat misinformation with increased scale and speed as successfully as community-driven efforts once did with spam. Nevertheless, general content moderation, especially for misinformation, is inherently more complex. Public perceptions of truth are often shaped by personal biases, political leanings, and cultural contexts, complicating consensus on what constitutes misleading content. This suggests that community efforts, while valuable, cannot replace the indispensable role of professional fact-checkers. Here we systemically examine the current approaches to misinformation detection across major platforms, explore the emerging role of community-driven moderation, and critically evaluate both the promises and challenges of crowd-checking at scale. △ Less

Submitted 26 May, 2025; originally announced May 2025.

Comments: 1 Figure, 2 tables

Value Profiles for Encoding Human Variation

Authors: Taylor Sorensen, Pushkar Mishra, Roma Patel, Michael Henry Tessler, Michiel Bakker, Georgina Evans, Iason Gabriel, Noah Goodman, Verena Rieser

Abstract: Modelling human variation in rating tasks is crucial for personalization, pluralistic model alignment, and computational social science. We propose representing individuals using natural language value profiles -- descriptions of underlying values compressed from in-context demonstrations -- along with a steerable decoder model that estimates individual ratings from a rater representation. To meas… ▽ More Modelling human variation in rating tasks is crucial for personalization, pluralistic model alignment, and computational social science. We propose representing individuals using natural language value profiles -- descriptions of underlying values compressed from in-context demonstrations -- along with a steerable decoder model that estimates individual ratings from a rater representation. To measure the predictive information in a rater representation, we introduce an information-theoretic methodology and find that demonstrations contain the most information, followed by value profiles, then demographics. However, value profiles effectively compress the useful information from demonstrations (>70% information preservation) and offer advantages in terms of scrutability, interpretability, and steerability. Furthermore, clustering value profiles to identify similarly behaving individuals better explains rater variation than the most predictive demographic groupings. Going beyond test set performance, we show that the decoder predictions change in line with semantic profile differences, are well-calibrated, and can help explain instance-level disagreement by simulating an annotator population. These results demonstrate that value profiles offer novel, predictive ways to describe individual variation beyond demographics or group information. △ Less

Submitted 30 September, 2025; v1 submitted 19 March, 2025; originally announced March 2025.

Comments: EMNLP 2025

Using Collective Dialogues and AI to Find Common Ground Between Israeli and Palestinian Peacebuilders

Authors: Andrew Konya, Luke Thorburn, Wasim Almasri, Oded Adomi Leshem, Ariel D. Procaccia, Lisa Schirch, Michiel A. Bakker

Abstract: A growing body of work has shown that AI-assisted methods -- leveraging large language models, social choice methods, and collective dialogues -- can help navigate polarization and surface common ground in controlled lab settings. But what can these approaches contribute in real-world contexts? We present a case study applying these techniques to find common ground between Israeli and Palestinian… ▽ More A growing body of work has shown that AI-assisted methods -- leveraging large language models, social choice methods, and collective dialogues -- can help navigate polarization and surface common ground in controlled lab settings. But what can these approaches contribute in real-world contexts? We present a case study applying these techniques to find common ground between Israeli and Palestinian peacebuilders in the period following October 7th, 2023. From April to July 2024 an iterative deliberative process combining LLMs, bridging-based ranking, and collective dialogues was conducted in partnership with the Alliance for Middle East Peace. Around 138 civil society peacebuilders participated including Israeli Jews, Palestinian citizens of Israel, and Palestinians from the West Bank and Gaza. The process resulted in a set of collective statements, including demands to world leaders, with at least 84% agreement from participants on each side. In this paper, we document the process, results, challenges, and important open questions. △ Less

Submitted 19 June, 2025; v1 submitted 3 March, 2025; originally announced March 2025.

Comments: Accepted at FAccT 2025

Tell Me Why: Incentivizing Explanations

Authors: Siddarth Srinivasan, Ezra Karger, Michiel Bakker, Yiling Chen

Abstract: Common sense suggests that when individuals explain why they believe something, we can arrive at more accurate conclusions than when they simply state what they believe. Yet, there is no known mechanism that provides incentives to elicit explanations for beliefs from agents. This likely stems from the fact that standard Bayesian models make assumptions (like conditional independence of signals) th… ▽ More Common sense suggests that when individuals explain why they believe something, we can arrive at more accurate conclusions than when they simply state what they believe. Yet, there is no known mechanism that provides incentives to elicit explanations for beliefs from agents. This likely stems from the fact that standard Bayesian models make assumptions (like conditional independence of signals) that preempt the need for explanations, in order to show efficient information aggregation. A natural justification for the value of explanations is that agents' beliefs tend to be drawn from overlapping sources of information, so agents' belief reports do not reveal all that needs to be known. Indeed, this work argues that rationales-explanations of an agent's private information-lead to more efficient aggregation by allowing agents to efficiently identify what information they share and what information is new. Building on this model of rationales, we present a novel 'deliberation mechanism' to elicit rationales from agents in which truthful reporting of beliefs and rationales is a perfect Bayesian equilibrium. △ Less

Submitted 18 February, 2025; originally announced February 2025.

Language Agents as Digital Representatives in Collective Decision-Making

Authors: Daniel Jarrett, Miruna Pîslar, Michiel A. Bakker, Michael Henry Tessler, Raphael Köster, Jan Balaguer, Romuald Elie, Christopher Summerfield, Andrea Tacchetti

Abstract: Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context, "representation" is the activity of making an individual's preferences present in the process via participation by a proxy agent -- i.e. their "representative". To this end, learned models of human behavior have the pot… ▽ More Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context, "representation" is the activity of making an individual's preferences present in the process via participation by a proxy agent -- i.e. their "representative". To this end, learned models of human behavior have the potential to fill this role, with practical implications for multi-agent scenario studies and mechanism design. In this work, we investigate the possibility of training \textit{language agents} to behave in the capacity of representatives of human agents, appropriately expressing the preferences of those individuals whom they stand for. First, we formalize the setting of \textit{collective decision-making} -- as the episodic process of interaction between a group of agents and a decision mechanism. On this basis, we then formalize the problem of \textit{digital representation} -- as the simulation of an agent's behavior to yield equivalent outcomes from the mechanism. Finally, we conduct an empirical case study in the setting of \textit{consensus-finding} among diverse humans, and demonstrate the feasibility of fine-tuning large language models to act as digital representatives. △ Less

Submitted 13 February, 2025; originally announced February 2025.

AI and the Future of Digital Public Squares

Authors: Beth Goldberg, Diana Acosta-Navas, Michiel Bakker, Ian Beacock, Matt Botvinick, Prateek Buch, Renée DiResta, Nandika Donthi, Nathanael Fast, Ravi Iyer, Zaria Jalan, Andrew Konya, Grace Kwak Danciu, Hélène Landemore, Alice Marwick, Carl Miller, Aviv Ovadya, Emily Saltz, Lisa Schirch, Dalit Shalom, Divya Siddarth, Felix Sieker, Christopher Small, Jonathan Stray, Audrey Tang , et al. (2 additional authors not shown)

Abstract: Two substantial technological advances have reshaped the public square in recent decades: first with the advent of the internet and second with the recent introduction of large language models (LLMs). LLMs offer opportunities for a paradigm shift towards more decentralized, participatory online spaces that can be used to facilitate deliberative dialogues at scale, but also create risks of exacerba… ▽ More Two substantial technological advances have reshaped the public square in recent decades: first with the advent of the internet and second with the recent introduction of large language models (LLMs). LLMs offer opportunities for a paradigm shift towards more decentralized, participatory online spaces that can be used to facilitate deliberative dialogues at scale, but also create risks of exacerbating societal schisms. Here, we explore four applications of LLMs to improve digital public squares: collective dialogue systems, bridging systems, community moderation, and proof-of-humanity systems. Building on the input from over 70 civil society experts and technologists, we argue that LLMs both afford promising opportunities to shift the paradigm for conversations at scale and pose distinct risks for digital public squares. We lay out an agenda for future research and investments in AI that will strengthen digital public squares and safeguard against potential misuses of AI. △ Less

Submitted 13 December, 2024; originally announced December 2024.

Comments: 40 pages, 5 figures

Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work

Authors: Aviv Ovadya, Kyle Redman, Luke Thorburn, Quan Ze Chen, Oliver Smith, Flynn Devine, Andrew Konya, Smitha Milli, Manon Revel, K. J. Kevin Feng, Amy X. Zhang, Bilva Chandra, Michiel A. Bakker, Atoosa Kasirzadeh

Abstract: This position paper argues that effectively "democratizing AI" requires democratic governance and alignment of AI, and that this is particularly valuable for decisions with systemic societal impacts. Initial steps -- such as Meta's Community Forums and Anthropic's Collective Constitutional AI -- have illustrated a promising direction, where democratic processes could be used to meaningfully improv… ▽ More This position paper argues that effectively "democratizing AI" requires democratic governance and alignment of AI, and that this is particularly valuable for decisions with systemic societal impacts. Initial steps -- such as Meta's Community Forums and Anthropic's Collective Constitutional AI -- have illustrated a promising direction, where democratic processes could be used to meaningfully improve public involvement and trust in critical decisions. To more concretely explore what increasingly democratic AI might look like, we provide a "Democracy Levels" framework and associated tools that: (i) define milestones toward meaningfully democratic AI, which is also crucial for substantively pluralistic, human-centered, participatory, and public-interest AI, (ii) can help guide organizations seeking to increase the legitimacy of their decisions on difficult AI governance and alignment questions, and (iii) support the evaluation of such efforts. △ Less

Submitted 21 August, 2025; v1 submitted 14 November, 2024; originally announced November 2024.

Comments: 31 pages. Accepted to the position paper track at ICML 2025. A previous version was presented at the Pluralistic Alignment Workshop at NeurIPS 2024. For ongoing work, see: https://democracylevels.org

Supernotes: Driving Consensus in Crowd-Sourced Fact-Checking

Authors: Soham De, Michiel A. Bakker, Jay Baxter, Martin Saveski

Abstract: X's Community Notes, a crowd-sourced fact-checking system, allows users to annotate potentially misleading posts. Notes rated as helpful by a diverse set of users are prominently displayed below the original post. While demonstrably effective at reducing misinformation's impact when notes are displayed, there is an opportunity for notes to appear on many more posts: for 91% of posts where at least… ▽ More X's Community Notes, a crowd-sourced fact-checking system, allows users to annotate potentially misleading posts. Notes rated as helpful by a diverse set of users are prominently displayed below the original post. While demonstrably effective at reducing misinformation's impact when notes are displayed, there is an opportunity for notes to appear on many more posts: for 91% of posts where at least one note is proposed, no notes ultimately achieve sufficient support from diverse users to be shown on the platform. This motivates the development of Supernotes: AI-generated notes that synthesize information from several existing community notes and are written to foster consensus among a diverse set of users. Our framework uses an LLM to generate many diverse Supernote candidates from existing proposed notes. These candidates are then evaluated by a novel scoring model, trained on millions of historical Community Notes ratings, selecting candidates that are most likely to be rated helpful by a diverse set of users. To test our framework, we ran a human subjects experiment in which we asked participants to compare the Supernotes generated by our framework to the best existing community notes for 100 sample posts. We found that participants rated the Supernotes as significantly more helpful, and when asked to choose between the two, preferred the Supernotes 75.2% of the time. Participants also rated the Supernotes more favorably than the best existing notes on quality, clarity, coverage, context, and argumentativeness. Finally, in a follow-up experiment, we asked participants to compare the Supernotes against LLM-generated summaries and found that the participants rated the Supernotes significantly more helpful, demonstrating that both the LLM-based candidate generation and the consensus-driven scoring play crucial roles in creating notes that effectively build consensus among diverse users. △ Less

Submitted 9 November, 2024; originally announced November 2024.

Comments: 11 pages, 10 figures (including appendix)

Evaluating Perceptual Deviations in Video See-Through Head-Mounted Displays while Utilizing Physical Touchscreens

Authors: Rudy De-Xin de Lange, Roemer Martin Bien Bakker, Tanja Johanna Juliana Bos

Abstract: Extended reality technology has become a useful tool in many applications, but still suffers from visual deviations that can hamper the utility of the technology. This paper discusses the types of persisting visual deviations experienced when observing the natural world through video see-through head-mounted displays. A generalizable method to measure the effect of these deviations on real-world i… ▽ More Extended reality technology has become a useful tool in many applications, but still suffers from visual deviations that can hamper the utility of the technology. This paper discusses the types of persisting visual deviations experienced when observing the natural world through video see-through head-mounted displays. A generalizable method to measure the effect of these deviations on real-world interaction is designed and used in a human-in-the-loop experiment. The experiment compared video see-through sight through an head-mounted display with normal eyesight in a static set-up, focusing on (camera) lens distortions and display deviations. Participants interacted with a real touchscreen, locating the position of flashed markers shortly after disappearance comparing both conditions to check for deviations in position and time. Results show significant larger mean distance errors between the interaction locations and the original marker positions for video see-through compared to normal eyesight. Moreover, errors increase towards the screen periphery. No significant distance error improvement over time was found, however, response times did significantly decrease for both types of sight. △ Less

Submitted 29 October, 2024; originally announced October 2024.

Comments: 10 pages. Preprint. A shortened 4-page version of this paper was accepted to the IEEE ISMAR2024 poster track

How will advanced AI systems impact democracy?

Authors: Christopher Summerfield, Lisa Argyle, Michiel Bakker, Teddy Collins, Esin Durmus, Tyna Eloundou, Iason Gabriel, Deep Ganguli, Kobi Hackenburg, Gillian Hadfield, Luke Hewitt, Saffron Huang, Helene Landemore, Nahema Marchal, Aviv Ovadya, Ariel Procaccia, Mathias Risse, Bruce Schneier, Elizabeth Seger, Divya Siddarth, Henrik Skaug Sætra, MH Tessler, Matthew Botvinick

Abstract: Advanced AI systems capable of generating humanlike text and multimodal content are now widely available. In this paper, we discuss the impacts that generative artificial intelligence may have on democratic processes. We consider the consequences of AI for citizens' ability to make informed choices about political representatives and issues (epistemic impacts). We ask how AI might be used to desta… ▽ More Advanced AI systems capable of generating humanlike text and multimodal content are now widely available. In this paper, we discuss the impacts that generative artificial intelligence may have on democratic processes. We consider the consequences of AI for citizens' ability to make informed choices about political representatives and issues (epistemic impacts). We ask how AI might be used to destabilise or support democratic mechanisms like elections (material impacts). Finally, we discuss whether AI will strengthen or weaken democratic principles (foundational impacts). It is widely acknowledged that new AI systems could pose significant challenges for democracy. However, it has also been argued that generative AI offers new opportunities to educate and learn from citizens, strengthen public discourse, help people find common ground, and to reimagine how democracies might work better. △ Less

Submitted 27 August, 2024; originally announced September 2024.

Comments: 25 pages

Fine-tuning language models to find agreement among humans with diverse preferences

Authors: Michiel A. Bakker, Martin J. Chadwick, Hannah R. Sheahan, Michael Henry Tessler, Lucy Campbell-Gillingham, Jan Balaguer, Nat McAleese, Amelia Glaese, John Aslanides, Matthew M. Botvinick, Christopher Summerfield

Abstract: Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a single "generic" user will confer more general alignment. Here, we embrace the heterogeneity of human preferences to consider a different challenge: how might… ▽ More Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a single "generic" user will confer more general alignment. Here, we embrace the heterogeneity of human preferences to consider a different challenge: how might a machine help people with diverse views find agreement? We fine-tune a 70 billion parameter LLM to generate statements that maximize the expected approval for a group of people with potentially diverse opinions. Human participants provide written opinions on thousands of questions touching on moral and political issues (e.g., "should we raise taxes on the rich?"), and rate the LLM's generated candidate consensus statements for agreement and quality. A reward model is then trained to predict individual preferences, enabling it to quantify and rank consensus statements in terms of their appeal to the overall group, defined according to different aggregation (social welfare) functions. The model produces consensus statements that are preferred by human users over those from prompted LLMs (>70%) and significantly outperforms a tight fine-tuned baseline that lacks the final ranking step. Further, our best model's consensus statements are preferred over the best human-generated opinions (>65%). We find that when we silently constructed consensus statements from only a subset of group members, those who were excluded were more likely to dissent, revealing the sensitivity of the consensus to individual contributions. These results highlight the potential to use LLMs to help groups of humans align their values with one another. △ Less

Submitted 27 November, 2022; originally announced November 2022.

Statistical discrimination in learning agents

Authors: Edgar A. Duéñez-Guzmán, Kevin R. McKee, Yiran Mao, Ben Coppin, Silvia Chiappa, Alexander Sasha Vezhnevets, Michiel A. Bakker, Yoram Bachrach, Suzanne Sadedin, William Isaac, Karl Tuyls, Joel Z. Leibo

Abstract: Undesired bias afflicts both human and algorithmic decision making, and may be especially prevalent when information processing trade-offs incentivize the use of heuristics. One primary example is \textit{statistical discrimination} -- selecting social partners based not on their underlying attributes, but on readily perceptible characteristics that covary with their suitability for the task at ha… ▽ More Undesired bias afflicts both human and algorithmic decision making, and may be especially prevalent when information processing trade-offs incentivize the use of heuristics. One primary example is \textit{statistical discrimination} -- selecting social partners based not on their underlying attributes, but on readily perceptible characteristics that covary with their suitability for the task at hand. We present a theoretical model to examine how information processing influences statistical discrimination and test its predictions using multi-agent reinforcement learning with various agent architectures in a partner choice-based social dilemma. As predicted, statistical discrimination emerges in agent policies as a function of both the bias in the training population and of agent architecture. All agents showed substantial statistical discrimination, defaulting to using the readily available correlates instead of the outcome relevant features. We show that less discrimination emerges with agents that use recurrent neural networks, and when their training environment has less bias. However, all agent algorithms we tried still exhibited substantial bias after learning in biased training populations. △ Less

Submitted 21 October, 2021; originally announced October 2021.

Comments: 29 pages, 10 figures

MSC Class: 68T07 (Primary) 91A26; 91-10; 93A16 (Secondary) ACM Class: I.2.11; I.2.0

Multi-task Semi-supervised Learning for Pulmonary Lobe Segmentation

Authors: Jingnan Jia, Zhiwei Zhai, M. Els Bakker, I. Hernandez Giron, Marius Staring, Berend C. Stoel

Abstract: Pulmonary lobe segmentation is an important preprocessing task for the analysis of lung diseases. Traditional methods relying on fissure detection or other anatomical features, such as the distribution of pulmonary vessels and airways, could provide reasonably accurate lobe segmentations. Deep learning based methods can outperform these traditional approaches, but require large datasets. Deep mult… ▽ More Pulmonary lobe segmentation is an important preprocessing task for the analysis of lung diseases. Traditional methods relying on fissure detection or other anatomical features, such as the distribution of pulmonary vessels and airways, could provide reasonably accurate lobe segmentations. Deep learning based methods can outperform these traditional approaches, but require large datasets. Deep multi-task learning is expected to utilize labels of multiple different structures. However, commonly such labels are distributed over multiple datasets. In this paper, we proposed a multi-task semi-supervised model that can leverage information of multiple structures from unannotated datasets and datasets annotated with different structures. A focused alternating training strategy is presented to balance the different tasks. We evaluated the trained model on an external independent CT dataset. The results show that our model significantly outperforms single-task alternatives, improving the mean surface distance from 7.174 mm to 4.196 mm. We also demonstrated that our approach is successful for different network architectures as backbones. △ Less

Submitted 22 April, 2021; originally announced April 2021.

Comments: 4 pages, to be published in ISBI 2021

Integrating Information Theory and Adversarial Learning for Cross-modal Retrieval

Authors: Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew

Abstract: Accurately matching visual and textual data in cross-modal retrieval has been widely studied in the multimedia community. To address these challenges posited by the heterogeneity gap and the semantic gap, we propose integrating Shannon information theory and adversarial learning. In terms of the heterogeneity gap, we integrate modality classification and information entropy maximization adversaria… ▽ More Accurately matching visual and textual data in cross-modal retrieval has been widely studied in the multimedia community. To address these challenges posited by the heterogeneity gap and the semantic gap, we propose integrating Shannon information theory and adversarial learning. In terms of the heterogeneity gap, we integrate modality classification and information entropy maximization adversarially. For this purpose, a modality classifier (as a discriminator) is built to distinguish the text and image modalities according to their different statistical properties. This discriminator uses its output probabilities to compute Shannon information entropy, which measures the uncertainty of the modality classification it performs. Moreover, feature encoders (as a generator) project uni-modal features into a commonly shared space and attempt to fool the discriminator by maximizing its output information entropy. Thus, maximizing information entropy gradually reduces the distribution discrepancy of cross-modal features, thereby achieving a domain confusion state where the discriminator cannot classify two modalities confidently. To reduce the semantic gap, Kullback-Leibler (KL) divergence and bi-directional triplet loss are used to associate the intra- and inter-modality similarity between features in the shared space. Furthermore, a regularization term based on KL-divergence with temperature scaling is used to calibrate the biased label classifier caused by the data imbalance issue. Extensive experiments with four deep models on four benchmarks are conducted to demonstrate the effectiveness of the proposed approach. △ Less

Submitted 11 April, 2021; originally announced April 2021.

Comments: Accepted by Pattern Recognition

Lifelong Person Re-Identification via Adaptive Knowledge Accumulation

Authors: Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew

Abstract: Person ReID methods always learn through a stationary domain that is fixed by the choice of a given dataset. In many contexts (e.g., lifelong learning), those methods are ineffective because the domain is continually changing in which case incremental learning over multiple domains is required potentially. In this work we explore a new and challenging ReID task, namely lifelong person re-identific… ▽ More Person ReID methods always learn through a stationary domain that is fixed by the choice of a given dataset. In many contexts (e.g., lifelong learning), those methods are ineffective because the domain is continually changing in which case incremental learning over multiple domains is required potentially. In this work we explore a new and challenging ReID task, namely lifelong person re-identification (LReID), which enables to learn continuously across multiple domains and even generalise on new and unseen domains. Following the cognitive processes in the human brain, we design an Adaptive Knowledge Accumulation (AKA) framework that is endowed with two crucial abilities: knowledge representation and knowledge operation. Our method alleviates catastrophic forgetting on seen domains and demonstrates the ability to generalize to unseen domains. Correspondingly, we also provide a new and large-scale benchmark for LReID. Extensive experiments demonstrate our method outperforms other competitors by a margin of 5.8% mAP in generalising evaluation. △ Less

Submitted 23 March, 2021; originally announced March 2021.

Comments: 10 pages, 5 figures, Accepted by CVPR2021

Modelling Cooperation in Network Games with Spatio-Temporal Complexity

Authors: Michiel A. Bakker, Richard Everett, Laura Weidinger, Iason Gabriel, William S. Isaac, Joel Z. Leibo, Edward Hughes

Abstract: The real world is awash with multi-agent problems that require collective action by self-interested agents, from the routing of packets across a computer network to the management of irrigation systems. Such systems have local incentives for individuals, whose behavior has an impact on the global outcome for the group. Given appropriate mechanisms describing agent interaction, groups may achieve s… ▽ More The real world is awash with multi-agent problems that require collective action by self-interested agents, from the routing of packets across a computer network to the management of irrigation systems. Such systems have local incentives for individuals, whose behavior has an impact on the global outcome for the group. Given appropriate mechanisms describing agent interaction, groups may achieve socially beneficial outcomes, even in the face of short-term selfish incentives. In many cases, collective action problems possess an underlying graph structure, whose topology crucially determines the relationship between local decisions and emergent global effects. Such scenarios have received great attention through the lens of network games. However, this abstraction typically collapses important dimensions, such as geometry and time, relevant to the design of mechanisms promoting cooperation. In parallel work, multi-agent deep reinforcement learning has shown great promise in modelling the emergence of self-organized cooperation in complex gridworld domains. Here we apply this paradigm in graph-structured collective action problems. Using multi-agent deep reinforcement learning, we simulate an agent society for a variety of plausible mechanisms, finding clear transitions between different equilibria over time. We define analytic tools inspired by related literatures to measure the social outcomes, and use these to draw conclusions about the efficacy of different environmental interventions. Our methods have implications for mechanism design in both human and artificial agent systems. △ Less

Submitted 13 February, 2021; originally announced February 2021.

Comments: AAMAS 2021

Self-supervised asymmetric deep hashing with margin-scalable constraint

Authors: Zhengyang Yu, Song Wu, Zhihao Dou, Erwin M. Bakker

Abstract: Due to its effectivity and efficiency, deep hashing approaches are widely used for large-scale visual search. However, it is still challenging to produce compact and discriminative hash codes for images associated with multiple semantics for two main reasons, 1) similarity constraints designed in most of the existing methods are based upon an oversimplified similarity assignment(i.e., 0 for instan… ▽ More Due to its effectivity and efficiency, deep hashing approaches are widely used for large-scale visual search. However, it is still challenging to produce compact and discriminative hash codes for images associated with multiple semantics for two main reasons, 1) similarity constraints designed in most of the existing methods are based upon an oversimplified similarity assignment(i.e., 0 for instance pairs sharing no label, 1 for instance pairs sharing at least 1 label), 2) the exploration in multi-semantic relevance are insufficient or even neglected in many of the existing methods. These problems significantly limit the discrimination of generated hash codes. In this paper, we propose a novel self-supervised asymmetric deep hashing method with a margin-scalable constraint(SADH) approach to cope with these problems. SADH implements a self-supervised network to sufficiently preserve semantic information in a semantic feature dictionary and a semantic code dictionary for the semantics of the given dataset, which efficiently and precisely guides a feature learning network to preserve multilabel semantic information using an asymmetric learning strategy. By further exploiting semantic dictionaries, a new margin-scalable constraint is employed for both precise similarity searching and robust hash code generation. Extensive empirical research on four popular benchmarks validates the proposed method and shows it outperforms several state-of-the-art approaches. △ Less

Submitted 23 July, 2021; v1 submitted 7 December, 2020; originally announced December 2020.

On the Exploration of Incremental Learning for Fine-grained Image Retrieval

Authors: Wei Chen, Yu Liu, Weiping Wang, Tinne Tuytelaars, Erwin M. Bakker, Michael Lew

Abstract: In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting. To this end, we propose an incremental learn… ▽ More In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting. To this end, we propose an incremental learning method to mitigate retrieval performance degradation caused by the forgetting issue. Without accessing any samples of the original classes, the classifier of the original network provides soft "labels" to transfer knowledge to train the adaptive network, so as to preserve the previous capability for classification. More importantly, a regularization function based on Maximum Mean Discrepancy is devised to minimize the discrepancy of new classes features from the original network and the adaptive network, respectively. Extensive experiments on two datasets show that our method effectively mitigates the catastrophic forgetting on the original classes while achieving high performance on the new classes. △ Less

Submitted 15 October, 2020; originally announced October 2020.

Comments: BMVC2020

Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification

Authors: Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew

Abstract: Visible-infrared person re-identification (VI-ReID) is a challenging and essential task in night-time intelligent surveillance systems. Except for the intra-modality variance that RGB-RGB person re-identification mainly overcomes, VI-ReID suffers from additional inter-modality variance caused by the inherent heterogeneous gap. To solve the problem, we present a carefully designed dual Gaussian-bas… ▽ More Visible-infrared person re-identification (VI-ReID) is a challenging and essential task in night-time intelligent surveillance systems. Except for the intra-modality variance that RGB-RGB person re-identification mainly overcomes, VI-ReID suffers from additional inter-modality variance caused by the inherent heterogeneous gap. To solve the problem, we present a carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively. Disentangling cross-modality identity-discriminable features leads to more robust retrieval for VI-ReID. To achieve efficient optimization like conventional VAE, we theoretically derive two variational inference terms for the MoG prior under the supervised setting, which not only restricts the identity-discriminable subspace so that the model explicitly handles the cross-modality intra-identity variance, but also enables the MoG distribution to avoid posterior collapse. Furthermore, we propose a triplet swap reconstruction (TSR) strategy to promote the above disentangling process. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on two VI-ReID datasets. △ Less

Submitted 6 August, 2020; originally announced August 2020.

Comments: Accepted by ACM MM 2020 poster. 12 pages, 10 appendixes

Assessing Disease Exposure Risk with Location Data: A Proposal for Cryptographic Preservation of Privacy

Authors: Alex Berke, Michiel Bakker, Praneeth Vepakomma, Kent Larson, Alex 'Sandy' Pentland

Abstract: Governments and researchers around the world are implementing digital contact tracing solutions to stem the spread of infectious disease, namely COVID-19. Many of these solutions threaten individual rights and privacy. Our goal is to break past the false dichotomy of effective versus privacy-preserving contact tracing. We offer an alternative approach to assess and communicate users' risk of expos… ▽ More Governments and researchers around the world are implementing digital contact tracing solutions to stem the spread of infectious disease, namely COVID-19. Many of these solutions threaten individual rights and privacy. Our goal is to break past the false dichotomy of effective versus privacy-preserving contact tracing. We offer an alternative approach to assess and communicate users' risk of exposure to an infectious disease while preserving individual privacy. Our proposal uses recent GPS location histories, which are transformed and encrypted, and a private set intersection protocol to interface with a semi-trusted authority. There have been other recent proposals for privacy-preserving contact tracing, based on Bluetooth and decentralization, that could further eliminate the need for trust in authority. However, solutions with Bluetooth are currently limited to certain devices and contexts while decentralization adds complexity. The goal of this work is two-fold: we aim to propose a location-based system that is more privacy-preserving than what is currently being adopted by governments around the world, and that is also practical to implement with the immediacy needed to stem a viral outbreak. △ Less

Submitted 8 April, 2020; v1 submitted 31 March, 2020; originally announced March 2020.

DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning

Authors: Michiel A. Bakker, Duy Patrick Tu, Humberto Riverón Valdés, Krishna P. Gummadi, Kush R. Varshney, Adrian Weller, Alex Pentland

Abstract: We introduce a framework for dynamic adversarial discovery of information (DADI), motivated by a scenario where information (a feature set) is used by third parties with unknown objectives. We train a reinforcement learning agent to sequentially acquire a subset of the information while balancing accuracy and fairness of predictors downstream. Based on the set of already acquired features, the age… ▽ More We introduce a framework for dynamic adversarial discovery of information (DADI), motivated by a scenario where information (a feature set) is used by third parties with unknown objectives. We train a reinforcement learning agent to sequentially acquire a subset of the information while balancing accuracy and fairness of predictors downstream. Based on the set of already acquired features, the agent decides dynamically to either collect more information from the set of available features or to stop and predict using the information that is currently available. Building on previous work exploring adversarial representation learning, we attain group fairness (demographic parity) by rewarding the agent with the adversary's loss, computed over the final feature set. Importantly, however, the framework provides a more general starting point for fair or private dynamic information discovery. Finally, we demonstrate empirically, using two real-world datasets, that we can trade-off fairness and predictive performance △ Less

Submitted 30 October, 2019; originally announced October 2019.

Comments: Accepted at NeurIPS 2019 HCML Workshop

Sherlock: A Deep Learning Approach to Semantic Data Type Detection

Authors: Madelon Hulsebos, Kevin Hu, Michiel Bakker, Emanuel Zgraggen, Arvind Satyanarayan, Tim Kraska, Çağatay Demiralp, César Hidalgo

Abstract: Correctly detecting the semantic type of data columns is crucial for data science tasks such as automated data cleaning, schema matching, and data discovery. Existing data preparation and analysis systems rely on dictionary lookups and regular expression matching to detect semantic types. However, these matching-based approaches often are not robust to dirty data and only detect a limited number o… ▽ More Correctly detecting the semantic type of data columns is crucial for data science tasks such as automated data cleaning, schema matching, and data discovery. Existing data preparation and analysis systems rely on dictionary lookups and regular expression matching to detect semantic types. However, these matching-based approaches often are not robust to dirty data and only detect a limited number of types. We introduce Sherlock, a multi-input deep neural network for detecting semantic types. We train Sherlock on $686,765$ data columns retrieved from the VizNet corpus by matching $78$ semantic types from DBpedia to column headers. We characterize each matched column with $1,588$ features describing the statistical properties, character distributions, word embeddings, and paragraph vectors of column values. Sherlock achieves a support-weighted F$_1$ score of $0.89$, exceeding that of machine learning baselines, dictionary and regular expression benchmarks, and the consensus of crowdsourced annotations. △ Less

Submitted 25 May, 2019; originally announced May 2019.

Comments: KDD'19

VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository

Authors: Kevin Hu, Neil Gaikwad, Michiel Bakker, Madelon Hulsebos, Emanuel Zgraggen, César Hidalgo, Tim Kraska, Guoliang Li, Arvind Satyanarayan, Çağatay Demiralp

Abstract: Researchers currently rely on ad hoc datasets to train automated visualization tools and evaluate the effectiveness of visualization designs. These exemplars often lack the characteristics of real-world datasets, and their one-off nature makes it difficult to compare different techniques. In this paper, we present VizNet: a large-scale corpus of over 31 million datasets compiled from open data rep… ▽ More Researchers currently rely on ad hoc datasets to train automated visualization tools and evaluate the effectiveness of visualization designs. These exemplars often lack the characteristics of real-world datasets, and their one-off nature makes it difficult to compare different techniques. In this paper, we present VizNet: a large-scale corpus of over 31 million datasets compiled from open data repositories and online visualization galleries. On average, these datasets comprise 17 records over 3 dimensions and across the corpus, we find 51% of the dimensions record categorical data, 44% quantitative, and only 5% temporal. VizNet provides the necessary common baseline for comparing visualization design techniques, and developing benchmark models and algorithms for automating visual analysis. To demonstrate VizNet's utility as a platform for conducting online crowdsourced experiments at scale, we replicate a prior study assessing the influence of user task and data distribution on visual encoding effectiveness, and extend it by considering an additional task: outlier detection. To contend with running such studies at scale, we demonstrate how a metric of perceptual effectiveness can be learned from experimental results, and show its predictive power across test datasets. △ Less

Submitted 11 May, 2019; originally announced May 2019.

Comments: CHI'19

Active Fairness in Algorithmic Decision Making

Authors: Alejandro Noriega-Campero, Michiel A. Bakker, Bernardo Garcia-Bulle, Alex Pentland

Abstract: Society increasingly relies on machine learning models for automated decision making. Yet, efficiency gains from automation have come paired with concern for algorithmic discrimination that can systematize inequality. Recent work has proposed optimal post-processing methods that randomize classification decisions for a fraction of individuals, in order to achieve fairness measures related to parit… ▽ More Society increasingly relies on machine learning models for automated decision making. Yet, efficiency gains from automation have come paired with concern for algorithmic discrimination that can systematize inequality. Recent work has proposed optimal post-processing methods that randomize classification decisions for a fraction of individuals, in order to achieve fairness measures related to parity in errors and calibration. These methods, however, have raised concern due to the information inefficiency, intra-group unfairness, and Pareto sub-optimality they entail. The present work proposes an alternative active framework for fair classification, where, in deployment, a decision-maker adaptively acquires information according to the needs of different groups or individuals, towards balancing disparities in classification performance. We propose two such methods, where information collection is adapted to group- and individual-level needs respectively. We show on real-world datasets that these can achieve: 1) calibration and single error parity (e.g., equal opportunity); and 2) parity in both false positive and false negative rates (i.e., equal odds). Moreover, we show that by leveraging their additional degree of freedom, active approaches can substantially outperform randomization-based classifiers previously considered optimal, while avoiding limitations such as intra-group unfairness. △ Less

Submitted 7 November, 2018; v1 submitted 28 September, 2018; originally announced October 2018.

VizML: A Machine Learning Approach to Visualization Recommendation

Authors: Kevin Z. Hu, Michiel A. Bakker, Stephen Li, Tim Kraska, César A. Hidalgo

Abstract: Data visualization should be accessible for all analysts with data, not just the few with technical expertise. Visualization recommender systems aim to lower the barrier to exploring basic visualizations by automatically generating results for analysts to search and select, rather than manually specify. Here, we demonstrate a novel machine learning-based approach to visualization recommendation th… ▽ More Data visualization should be accessible for all analysts with data, not just the few with technical expertise. Visualization recommender systems aim to lower the barrier to exploring basic visualizations by automatically generating results for analysts to search and select, rather than manually specify. Here, we demonstrate a novel machine learning-based approach to visualization recommendation that learns visualization design choices from a large corpus of datasets and associated visualizations. First, we identify five key design choices made by analysts while creating visualizations, such as selecting a visualization type and choosing to encode a column along the X- or Y-axis. We train models to predict these design choices using one million dataset-visualization pairs collected from a popular online visualization platform. Neural networks predict these design choices with high accuracy compared to baseline models. We report and interpret feature importances from one of these baseline models. To evaluate the generalizability and uncertainty of our approach, we benchmark with a crowdsourced test set, and show that the performance of our model is comparable to human performance when predicting consensus visualization type, and exceeds that of other ML-based systems. △ Less

Submitted 14 August, 2018; originally announced August 2018.

Model-order reduction of biochemical reaction networks

Authors: Shodhan Rao, Arjan van der Schaft, Karen van Eunen, Barbara M. Bakker, Bayu Jayawardhana

Abstract: In this paper we propose a model-order reduction method for chemical reaction networks governed by general enzyme kinetics, including the mass-action and Michaelis-Menten kinetics. The model-order reduction method is based on the Kron reduction of the weighted Laplacian matrix which describes the graph structure of complexes in the chemical reaction network. We apply our method to a yeast glycolys… ▽ More In this paper we propose a model-order reduction method for chemical reaction networks governed by general enzyme kinetics, including the mass-action and Michaelis-Menten kinetics. The model-order reduction method is based on the Kron reduction of the weighted Laplacian matrix which describes the graph structure of complexes in the chemical reaction network. We apply our method to a yeast glycolysis model, where the simulation result shows that the transient behaviour of a number of key metabolites of the reduced-order model is in good agreement with those of the full-order model. △ Less

Submitted 11 December, 2012; originally announced December 2012.

Comments: 7 pages, 5 figures. arXiv admin note: substantial text overlap with arXiv:1211.6643, arXiv:1110.6078

Alignment of Microtubule Imagery

Authors: Feiyang Yu, Ard Oerlemans, Erwin M. Bakker

Abstract: This work discusses preliminary work aimed at simulating and visualizing the growth process of a tiny structure inside the cell---the microtubule. Difficulty of recording the process lies in the fact that the tissue preparation method for electronic microscopes is highly destructive to live cells. Here in this paper, our approach is to take pictures of microtubules at different time slots and then… ▽ More This work discusses preliminary work aimed at simulating and visualizing the growth process of a tiny structure inside the cell---the microtubule. Difficulty of recording the process lies in the fact that the tissue preparation method for electronic microscopes is highly destructive to live cells. Here in this paper, our approach is to take pictures of microtubules at different time slots and then appropriately combine these images into a coherent video. Experimental results are given on real data. △ Less

Submitted 30 May, 2011; originally announced May 2011.

SPARK00: A Benchmark Package for the Compiler Evaluation of Irregular/Sparse Codes

Authors: H. L. A. van der Spek, E. M. Bakker, H. A. G. Wijshoff

Abstract: We propose a set of benchmarks that specifically targets a major cause of performance degradation in high performance computing platforms: irregular access patterns. These benchmarks are meant to be used to asses the performance of optimizing compilers on codes with a varying degree of irregular access. The irregularity caused by the use of pointers and indirection arrays are a major challenge f… ▽ More We propose a set of benchmarks that specifically targets a major cause of performance degradation in high performance computing platforms: irregular access patterns. These benchmarks are meant to be used to asses the performance of optimizing compilers on codes with a varying degree of irregular access. The irregularity caused by the use of pointers and indirection arrays are a major challenge for optimizing compilers. Codes containing such patterns are notoriously hard to optimize but they have a huge impact on the performance of modern architectures, which are under-utilized when encountering irregular memory accesses. In this paper, a set of benchmarks is described that explicitly measures the performance of kernels containing a variety of different access patterns found in real world applications. By offering a varying degree of complexity, we provide a platform for measuring the effectiveness of transformations. The difference in complexity stems from a difference in traversal patterns, the use of multiple indirections and control flow statements. The kernels used cover a variety of different access patterns, namely pointer traversals, indirection arrays, dynamic loop bounds and run-time dependent if-conditions. The kernels are small enough to be fully understood which makes this benchmark set very suitable for the evaluation of restructuring transformations. △ Less

Submitted 26 May, 2008; originally announced May 2008.