Showing 1–20 of 20 results for author: Coleman, C

Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning

Authors: Ali Dasdan, Manan Shah, W. Russell Neuman, Chad Coleman, Kund Meghani, Safinah Ali

Abstract: Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it. We use Transluce, an AI-driven mechanistic-interpretability platform, to examine LLaMA 3.1-8B-Instruct on 54 moral prompts in four batteries: 17 dilemmas, policy, and meta-ethical questions (B1); 6 role-playing scenarios (B3); and a controlled trolley contrast varying… ▽ More Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it. We use Transluce, an AI-driven mechanistic-interpretability platform, to examine LLaMA 3.1-8B-Instruct on 54 moral prompts in four batteries: 17 dilemmas, policy, and meta-ethical questions (B1); 6 role-playing scenarios (B3); and a controlled trolley contrast varying the switching mechanism with people fixed (B4, 15 prompts) or identity attributes with mechanism fixed (B5, 16 prompts). Two complementary metric families, five cluster-level metrics and a six-metric neuron-level panel, converge on a Situational Anchor Effect: domain-specific representations dominate the top of the activation list across every battery. The model's ethics-labeled capacity stays essentially constant; its salience (rank, priority, top-of-list presence) is highly sensitive to the interpretive frame the prompt selects. The B4-vs-B5 contrast confirms the model attends to whichever surface feature varies: aggregate ethics metrics are indistinguishable, but the dominant non-ethics distractor mirrors the design. A multi-temperature audit identifies a candidate ethics neuron (L16/N3837) stable across temperatures; a cross-model behavioral proxy on two frontier models yields preliminary evidence of divergence in self-reported moral focus, consistent with an Alignment Wrapper in which RLHF re-orders surface text without removing underlying domain-first frames. We unify these as Frame-Conditioned Moral Computation: the prompt's surface vocabulary selects a feature manifold, and the moral conclusion is downstream of that selection. Behavioral alignment must be supplemented by Mechanistic Alignment: a research program asking whether ethics-related features can be shown causally privileged under controlled frame variation, not merely loud in the explanation. △ Less

Submitted 13 June, 2026; originally announced June 2026.

Comments: 47 pages, 10 figures

Six Llamas: Comparative Religious Ethics Through LoRA-Adapted Language Models

Authors: Chad Coleman, W. Russell Neuman, Manan Shah, Ali Dasdan, Matthew Crispi, Morris Chiang, Zack Leitman, Mustafa Poonawala

Abstract: We present Six Llamas, a comparative study examining whether large language models fine-tuned on distinct religious corpora encode systematically different patterns of ethical reasoning. Six variants of Meta-Llama-3.1-8B are constructed: one unmodified control and five LoRA-adapted models trained exclusively on the sacred and theological texts of Christianity, Islam, Judaism, Hinduism, or Buddhism… ▽ More We present Six Llamas, a comparative study examining whether large language models fine-tuned on distinct religious corpora encode systematically different patterns of ethical reasoning. Six variants of Meta-Llama-3.1-8B are constructed: one unmodified control and five LoRA-adapted models trained exclusively on the sacred and theological texts of Christianity, Islam, Judaism, Hinduism, or Buddhism. All six models are probed with an identical battery of 17 standardized ethical prompts spanning moral dilemmas, game-theoretic scenarios, public policy questions, and moral-psychological self-assessments. To assess robustness and reproducibility, we implement a multi-temperature sampling design spanning ten temperature settings. We compute response consistency metrics, pairwise inter-model agreement rates, temperature sensitivity coefficients across four prompt domains, and run-to-run stability analyses. Findings show that LoRA-adapted models produce ethical reasoning patterns that are (a) systematically differentiated from the base model, (b) consistent with the moral logics of their training traditions, (c) structured along interpretable dimensions in moral-philosophical space, (d) core ethical positions remain stable across temperature variations for high-consensus dilemmas. The Trolley Problem achieves 100% consistency across all models and temperatures, while (e) tradition-specific divergence intensifies at higher temperatures in morally contested domains, and (f) the base model exhibits the highest overall response consistency (mean 88.3%), suggesting LoRA adaptation introduces both tradition-specific signal and increased sampling sensitivity. The study offers a proof-of-concept for the condensate comparative method using differentially trained language models as instruments for cultural and ethical analysis and identifies specific criteria for falsification and planned extensions. △ Less

Submitted 20 April, 2026; originally announced April 2026.

Comments: 51 pages, 14 figures. We present Six Llamas, a comparative study examining whether Llama-3.1-8B models fine-tuned on distinct religious corpora encode systematically different patterns of ethical reasoning. Five LoRA-adapted variants are constructed for Christianity, Islam, Judaism, Hinduism, and Buddhism. For theoretical background on the condensate comparative method, see arXiv:2603.07329

The Third Ambition: Artificial Intelligence and the Science of Human Behavior

Authors: W. Russell Neuman, Chad Coleman

Abstract: Contemporary artificial intelligence research has been organized around two dominant ambitions: productivity, which treats AI systems as tools for accelerating work and economic output, and alignment, which focuses on ensuring that increasingly capable systems behave safely and in accordance with human values. This paper articulates and develops a third, emerging ambition: the use of large languag… ▽ More Contemporary artificial intelligence research has been organized around two dominant ambitions: productivity, which treats AI systems as tools for accelerating work and economic output, and alignment, which focuses on ensuring that increasingly capable systems behave safely and in accordance with human values. This paper articulates and develops a third, emerging ambition: the use of large language models (LLMs) as scientific instruments for studying human behavior, culture, and moral reasoning. Trained on unprecedented volumes of human-produced text, LLMs encode large-scale regularities in how people argue, justify, narrate, and negotiate norms across social domains. We argue that these models can be understood as condensates of human symbolic behavior, compressed, generative representations that render patterns of collective discourse computationally accessible. The paper situates this third ambition within long-standing traditions of computational social science, content analysis, survey research, and comparative-historical inquiry, while clarifying the epistemic limits of treating model output as evidence. We distinguish between base models and fine-tuned systems, showing how alignment interventions can systematically reshape or obscure the cultural regularities learned during pretraining, and we identify instruct-only and modular adaptation regimes as pragmatic compromises for behavioral research. We review emerging methodological approaches including prompt-based experiments, synthetic population sampling, comparative-historical modeling, and ablation studies and show how each maps onto familiar social-scientific designs while operating at unprecedented scale. △ Less

Submitted 7 March, 2026; originally announced March 2026.

"Amazing, They All Lean Left" -- Analyzing the Political Temperaments of Current LLMs

Authors: W. Russell Neuman, Chad Coleman, Ali Dasdan, Safinah Ali, Manan Shah, Kund Meghani

Abstract: Recent studies have revealed a consistent liberal orientation in the ethical and political responses generated by most commercial large language models (LLMs), yet the underlying causes and resulting implications remain unclear. This paper systematically investigates the political temperament of seven prominent LLMs - OpenAI's GPT-4o, Anthropic's Claude Sonnet 4, Perplexity (Sonar Large), Google's… ▽ More Recent studies have revealed a consistent liberal orientation in the ethical and political responses generated by most commercial large language models (LLMs), yet the underlying causes and resulting implications remain unclear. This paper systematically investigates the political temperament of seven prominent LLMs - OpenAI's GPT-4o, Anthropic's Claude Sonnet 4, Perplexity (Sonar Large), Google's Gemini 2.5 Flash, Meta AI's Llama 4, Mistral 7b Le Chat and High-Flyer's DeepSeek R1 -- using a multi-pronged approach that includes Moral Foundations Theory, a dozen established political ideology scales and a new index of current political controversies. We find strong and consistent prioritization of liberal-leaning values, particularly care and fairness, across most models. Further analysis attributes this trend to four overlapping factors: Liberal-leaning training corpora, reinforcement learning from human feedback (RLHF), the dominance of liberal frameworks in academic ethical discourse and safety-driven fine-tuning practices. We also distinguish between political "bias" and legitimate epistemic differences, cautioning against conflating the two. A comparison of base and fine-tuned model pairs reveals that fine-tuning generally increases liberal lean, an effect confirmed through both self-report and empirical testing. We argue that this "liberal tilt" is not a programming error or the personal preference of programmers but an emergent property of training on democratic rights-focused discourse. Finally, we propose that LLMs may indirectly echo John Rawls' famous veil-of ignorance philosophical aspiration, reflecting a moral stance unanchored to personal identity or interest. Rather than undermining democratic discourse, this pattern may offer a new lens through which to examine collective reasoning. △ Less

Submitted 8 July, 2025; originally announced July 2025.

The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approach

Authors: Chad Coleman, W. Russell Neuman, Ali Dasdan, Safinah Ali, Manan Shah

Abstract: As large language models (LLMs) are increasingly deployed in consequential decision-making contexts, systematically assessing their ethical reasoning capabilities becomes a critical imperative. This paper introduces the Priorities in Reasoning and Intrinsic Moral Evaluation (PRIME) framework--a comprehensive methodology for analyzing moral priorities across foundational ethical dimensions includin… ▽ More As large language models (LLMs) are increasingly deployed in consequential decision-making contexts, systematically assessing their ethical reasoning capabilities becomes a critical imperative. This paper introduces the Priorities in Reasoning and Intrinsic Moral Evaluation (PRIME) framework--a comprehensive methodology for analyzing moral priorities across foundational ethical dimensions including consequentialist-deontological reasoning, moral foundations theory, and Kohlberg's developmental stages. We apply this framework to six leading LLMs through a dual-protocol approach combining direct questioning and response analysis to established ethical dilemmas. Our analysis reveals striking patterns of convergence: all evaluated models demonstrate strong prioritization of care/harm and fairness/cheating foundations while consistently underweighting authority, loyalty, and sanctity dimensions. Through detailed examination of confidence metrics, response reluctance patterns, and reasoning consistency, we establish that contemporary LLMs (1) produce decisive ethical judgments, (2) demonstrate notable cross-model alignment in moral decision-making, and (3) generally correspond with empirically established human moral preferences. This research contributes a scalable, extensible methodology for ethical benchmarking while highlighting both the promising capabilities and systematic limitations in current AI moral reasoning architectures--insights critical for responsible development as these systems assume increasingly significant societal roles. △ Less

Submitted 27 April, 2025; originally announced April 2025.

Comments: 25 pages, 8 figures

Auditing the Ethical Logic of Generative AI Models

Authors: W. Russell Neuman, Chad Coleman, Ali Dasdan, Safinah Ali, Manan Shah

Abstract: As generative AI models become increasingly integrated into high-stakes domains, the need for robust methods to evaluate their ethical reasoning becomes increasingly important. This paper introduces a five-dimensional audit model -- assessing Analytic Quality, Breadth of Ethical Considerations, Depth of Explanation, Consistency, and Decisiveness -- to evaluate the ethical logic of leading large la… ▽ More As generative AI models become increasingly integrated into high-stakes domains, the need for robust methods to evaluate their ethical reasoning becomes increasingly important. This paper introduces a five-dimensional audit model -- assessing Analytic Quality, Breadth of Ethical Considerations, Depth of Explanation, Consistency, and Decisiveness -- to evaluate the ethical logic of leading large language models (LLMs). Drawing on traditions from applied ethics and higher-order thinking, we present a multi-battery prompt approach, including novel ethical dilemmas, to probe the models' reasoning across diverse contexts. We benchmark seven major LLMs finding that while models generally converge on ethical decisions, they vary in explanatory rigor and moral prioritization. Chain-of-Thought prompting and reasoning-optimized models significantly enhance performance on our audit metrics. This study introduces a scalable methodology for ethical benchmarking of AI systems and highlights the potential for AI to complement human moral reasoning in complex decision-making contexts. △ Less

Submitted 24 April, 2025; originally announced April 2025.

AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons

Authors: Shaona Ghosh, Heather Frase, Adina Williams, Sarah Luger, Paul Röttger, Fazl Barez, Sean McGregor, Kenneth Fricklas, Mala Kumar, Quentin Feuillade--Montixi, Kurt Bollacker, Felix Friedrich, Ryan Tsang, Bertie Vidgen, Alicia Parrish, Chris Knotz, Eleonora Presani, Jonathan Bennion, Marisa Ferrara Boston, Mike Kuniavsky, Wiebke Hutiri, James Ezick, Malek Ben Salem, Rajat Sahay, Sujata Goswami , et al. (77 additional authors not shown)

Abstract: The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability. Its development employed an open process that included participants from multiple fields. The benchmark evaluates an AI system's resistance… ▽ More The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability. Its development employed an open process that included participants from multiple fields. The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories, including violent crimes, nonviolent crimes, sex-related crimes, child sexual exploitation, indiscriminate weapons, suicide and self-harm, intellectual property, privacy, defamation, hate, sexual content, and specialized advice (election, financial, health, legal). Our method incorporates a complete assessment standard, extensive prompt datasets, a novel evaluation framework, a grading and reporting system, and the technical as well as organizational infrastructure for long-term support and evolution. In particular, the benchmark employs an understandable five-tier grading scale (Poor to Excellent) and incorporates an innovative entropy-based system-response evaluation. In addition to unveiling the benchmark, this report also identifies limitations of our method and of building safety benchmarks generally, including evaluator uncertainty and the constraints of single-turn interactions. This work represents a crucial step toward establishing global standards for AI risk and reliability evaluation while acknowledging the need for continued development in areas such as multiturn interactions, multimodal understanding, coverage of additional languages, and emerging hazard categories. Our findings provide valuable insights for model developers, system integrators, and policymakers working to promote safer AI deployment. △ Less

Submitted 18 April, 2025; v1 submitted 19 February, 2025; originally announced March 2025.

Comments: 51 pages, 8 figures and an appendix

Analyzing the Ethical Logic of Eight Large Language Models

Authors: W. Russell Neuman, Chad Coleman, Manan Shah

Abstract: This study examines the expressed ethical logic of eight prominent large language models from OpenAI, Meta, Perplexity, Anthropic, Google, Mistral, DeepSeek, and xAI. Each model answered direct questions about its ethical principles and responded to five classic moral dilemmas. Responses were analyzed using the consequentialist/deontological distinction, Moral Foundations Theory, and Kohlbergs sta… ▽ More This study examines the expressed ethical logic of eight prominent large language models from OpenAI, Meta, Perplexity, Anthropic, Google, Mistral, DeepSeek, and xAI. Each model answered direct questions about its ethical principles and responded to five classic moral dilemmas. Responses were analyzed using the consequentialist/deontological distinction, Moral Foundations Theory, and Kohlbergs stages of moral development. Across models, ethical judgments were broadly convergent and typically emphasized harm minimization, fairness, and contextual qualification. The models nevertheless differed in their willingness to decide, the rationales used to defend choices, and the relative weight assigned to rules, outcomes, role obligations, and interpersonal considerations. Their self-descriptions were erudite, cautious, and strongly shaped by a conversational persona. The analysis of self-reports has been central to the study of human psychology and communication. We propose, with appropriate cautions, it can enhance our understanding of how artificial intelligence works and how it may be able to augment human ethical behavior △ Less

Submitted 24 July, 2026; v1 submitted 15 January, 2025; originally announced January 2025.

Introducing v0.5 of the AI Safety Benchmark from MLCommons

Authors: Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed, Victor Akinwande, Namir Al-Nuaimi, Najla Alfaraj, Elie Alhajjar, Lora Aroyo, Trupti Bavalatti, Max Bartolo, Borhane Blili-Hamelin, Kurt Bollacker, Rishi Bomassani, Marisa Ferrara Boston, Siméon Campos, Kal Chakra, Canyu Chen, Cody Coleman, Zacharie Delpierre Coudert, Leon Derczynski, Debojyoti Dutta, Ian Eisenberg, James Ezick, Heather Frase, Brian Fuller , et al. (75 additional authors not shown)

Abstract: This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models. We introduce a principled approach to specifying and constructing the benchmark, which for v0.5 covers only a single use case (an adult chatting to a general-pu… ▽ More This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models. We introduce a principled approach to specifying and constructing the benchmark, which for v0.5 covers only a single use case (an adult chatting to a general-purpose assistant in English), and a limited set of personas (i.e., typical users, malicious users, and vulnerable users). We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0.5 benchmark. We plan to release version 1.0 of the AI Safety Benchmark by the end of 2024. The v1.0 benchmark will provide meaningful insights into the safety of AI systems. However, the v0.5 benchmark should not be used to assess the safety of AI systems. We have sought to fully document the limitations, flaws, and challenges of v0.5. This release of v0.5 of the AI Safety Benchmark includes (1) a principled approach to specifying and constructing the benchmark, which comprises use cases, types of systems under test (SUTs), language and context, personas, tests, and test items; (2) a taxonomy of 13 hazard categories with definitions and subcategories; (3) tests for seven of the hazard categories, each comprising a unique set of test items, i.e., prompts. There are 43,090 test items in total, which we created with templates; (4) a grading system for AI systems against the benchmark; (5) an openly available platform, and downloadable tool, called ModelBench that can be used to evaluate the safety of AI systems on the benchmark; (6) an example evaluation report which benchmarks the performance of over a dozen openly available chat-tuned language models; (7) a test specification for the benchmark. △ Less

Submitted 13 May, 2024; v1 submitted 18 April, 2024; originally announced April 2024.

DMLR: Data-centric Machine Learning Research -- Past, Present and Future

Authors: Luis Oala, Manil Maskey, Lilith Bat-Leah, Alicia Parrish, Nezihe Merve Gürel, Tzu-Sheng Kuo, Yang Liu, Rotem Dror, Danilo Brajovic, Xiaozhe Yao, Max Bartolo, William A Gaviria Rojas, Ryan Hileman, Rainier Aliment, Michael W. Mahoney, Meg Risdal, Matthew Lease, Wojciech Samek, Debojyoti Dutta, Curtis G Northcutt, Cody Coleman, Braden Hancock, Bernard Koch, Girmaw Abebe Tadesse, Bojan Karlaš , et al. (13 additional authors not shown)

Abstract: Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will advance machine learning science. We chart a path forward as a collective effort to sustain the creation and maintenance of these datasets and methods tow… ▽ More Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will advance machine learning science. We chart a path forward as a collective effort to sustain the creation and maintenance of these datasets and methods towards positive scientific, societal and business impact. △ Less

Submitted 1 June, 2024; v1 submitted 21 November, 2023; originally announced November 2023.

Comments: Published in the Journal of Data-centric Machine Learning Research (DMLR) at https://data.mlr.press/assets/pdf/v01-5.pdf

Do Cloud Developers Prefer CLIs or Web Consoles? CLIs Mostly, Though It Varies by Task

Authors: Cora Coleman, William G. Griswold, Nick Mitchell

Abstract: Despite the increased importance of Cloud tooling, and many large-scale studies of Cloud users, research has yet to answer what tool modalities (e.g. CLI or web console) developers prefer. In formulating our studies, we quickly found that preference varies heavily based on the programming task at hand. To address this gap, we conducted a two-part research study that quantifies modality preference… ▽ More Despite the increased importance of Cloud tooling, and many large-scale studies of Cloud users, research has yet to answer what tool modalities (e.g. CLI or web console) developers prefer. In formulating our studies, we quickly found that preference varies heavily based on the programming task at hand. To address this gap, we conducted a two-part research study that quantifies modality preference as a function of programming task. Part one surveys how preference for three tool modalities (CLI, IDE, web console) varies across three classes of task (CRUD, debugging, monitoring). The survey shows, among 60 respondents, developers most prefer the CLI modality, especially for CRUD tasks. Monitoring tasks are the exception for which developers prefer the web console. Part two observes how four participants complete a task using the kubectl CLI and the OpenShift web console. All four participants prefer using the CLI to accomplish the task. △ Less

Submitted 15 September, 2022; originally announced September 2022.

Comments: 13 pages, 7 figures

DataPerf: Benchmarks for Data-Centric AI Development

Authors: Mark Mazumder, Colby Banbury, Xiaozhe Yao, Bojan Karlaš, William Gaviria Rojas, Sudnya Diamos, Greg Diamos, Lynn He, Alicia Parrish, Hannah Rose Kirk, Jessica Quaye, Charvi Rastogi, Douwe Kiela, David Jurado, David Kanter, Rafael Mosquera, Juan Ciro, Lora Aroyo, Bilge Acun, Lingjiao Chen, Mehul Smriti Raje, Max Bartolo, Sabri Eyuboglu, Amirata Ghorbani, Emmett Goodman , et al. (20 additional authors not shown)

Abstract: Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems. Neglecting the fundamental importance of data has given rise to inaccuracy, bias, and fragility in real-world applications, and research is hindered by saturation across existing datase… ▽ More Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems. Neglecting the fundamental importance of data has given rise to inaccuracy, bias, and fragility in real-world applications, and research is hindered by saturation across existing dataset benchmarks. In response, we present DataPerf, a community-led benchmark suite for evaluating ML datasets and data-centric algorithms. We aim to foster innovation in data-centric AI through competition, comparability, and reproducibility. We enable the ML community to iterate on datasets, instead of just architectures, and we provide an open, online platform with multiple rounds of challenges to support this iterative development. The first iteration of DataPerf contains five benchmarks covering a wide spectrum of data-centric techniques, tasks, and modalities in vision, speech, acquisition, debugging, and diffusion prompting, and we support hosting new contributed benchmarks from the community. The benchmarks, online evaluation platform, and baseline implementations are open source, and the MLCommons Association will maintain DataPerf to ensure long-term benefits to academia and industry. △ Less

Submitted 13 October, 2023; v1 submitted 20 July, 2022; originally announced July 2022.

Comments: NeurIPS 2023 Datasets and Benchmarks Track

AI training resources for GLAM: a snapshot

Authors: Andrew Darby, Catherine Nicole Coleman, Claudia Engel, Daniel van Strien, Mike Trizna, Zachary W. Painter

Abstract: We take a snapshot of current resources available for teaching and learning AI with a focus on the Galleries, Libraries, Archives and Museums (GLAM) community. The review was carried out in 2021 and 2022. The review provides an overview of material we identified as being relevant, offers a description of this material and makes recommendations for future work in this area. We take a snapshot of current resources available for teaching and learning AI with a focus on the Galleries, Libraries, Archives and Museums (GLAM) community. The review was carried out in 2021 and 2022. The review provides an overview of material we identified as being relevant, offers a description of this material and makes recommendations for future work in this area. △ Less

Submitted 10 May, 2022; originally announced May 2022.

MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation

Authors: Alexandros Karargyris, Renato Umeton, Micah J. Sheller, Alejandro Aristizabal, Johnu George, Srini Bala, Daniel J. Beutel, Victor Bittorf, Akshay Chaudhari, Alexander Chowdhury, Cody Coleman, Bala Desinghu, Gregory Diamos, Debo Dutta, Diane Feddema, Grigori Fursin, Junyi Guo, Xinyuan Huang, David Kanter, Satyananda Kashyap, Nicholas Lane, Indranil Mallick, Pietro Mascagni, Virendra Mehta, Vivek Natarajan , et al. (17 additional authors not shown)

Abstract: Medical AI has tremendous potential to advance healthcare by supporting the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving provider and patient experience. We argue that unlocking this potential requires a systematic way to measure the performance of medical AI models on large-scale heterogeneous data. To meet this need, we are building MedPerf,… ▽ More Medical AI has tremendous potential to advance healthcare by supporting the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving provider and patient experience. We argue that unlocking this potential requires a systematic way to measure the performance of medical AI models on large-scale heterogeneous data. To meet this need, we are building MedPerf, an open framework for benchmarking machine learning in the medical domain. MedPerf will enable federated evaluation in which models are securely distributed to different facilities for evaluation, thereby empowering healthcare organizations to assess and verify the performance of AI models in an efficient and human-supervised process, while prioritizing privacy. We describe the current challenges healthcare and AI communities face, the need for an open platform, the design philosophy of MedPerf, its current implementation status, and our roadmap. We call for researchers and organizations to join us in creating the MedPerf open benchmarking platform. △ Less

Submitted 28 December, 2021; v1 submitted 29 September, 2021; originally announced October 2021.

Similarity Search for Efficient Active Learning and Search of Rare Concepts

Authors: Cody Coleman, Edward Chou, Julian Katz-Samuels, Sean Culatana, Peter Bailis, Alexander C. Berg, Robert Nowak, Roshan Sumbaly, Matei Zaharia, I. Zeki Yalniz

Abstract: Many active learning and search approaches are intractable for large-scale industrial settings with billions of unlabeled examples. Existing approaches search globally for the optimal examples to label, scaling linearly or even quadratically with the unlabeled data. In this paper, we improve the computational efficiency of active learning and search methods by restricting the candidate pool for la… ▽ More Many active learning and search approaches are intractable for large-scale industrial settings with billions of unlabeled examples. Existing approaches search globally for the optimal examples to label, scaling linearly or even quadratically with the unlabeled data. In this paper, we improve the computational efficiency of active learning and search methods by restricting the candidate pool for labeling to the nearest neighbors of the currently labeled set instead of scanning over all of the unlabeled data. We evaluate several selection strategies in this setting on three large-scale computer vision datasets: ImageNet, OpenImages, and a de-identified and aggregated dataset of 10 billion images provided by a large internet company. Our approach achieved similar mean average precision and recall as the traditional global approach while reducing the computational cost of selection by up to three orders of magnitude, thus enabling web-scale active learning. △ Less

Submitted 22 July, 2021; v1 submitted 30 June, 2020; originally announced July 2020.

MLPerf Inference Benchmark

Authors: Vijay Janapa Reddi, Christine Cheng, David Kanter, Peter Mattson, Guenther Schmuelling, Carole-Jean Wu, Brian Anderson, Maximilien Breughe, Mark Charlebois, William Chou, Ramesh Chukka, Cody Coleman, Sam Davis, Pan Deng, Greg Diamos, Jared Duke, Dave Fick, J. Scott Gardner, Itay Hubara, Sachin Idgunji, Thomas B. Jablin, Jeff Jiao, Tom St. John, Pankaj Kanwar, David Lee , et al. (22 additional authors not shown)

Abstract: Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organizations are building ML inference chips, and the systems that incorporate existing models span at least three orders of magnitude in power consumption and five orders of magnitude in performance; they range from embedded devic… ▽ More Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organizations are building ML inference chips, and the systems that incorporate existing models span at least three orders of magnitude in power consumption and five orders of magnitude in performance; they range from embedded devices to data-center solutions. Fueling the hardware are a dozen or more software frameworks and libraries. The myriad combinations of ML hardware and ML software make assessing ML-system performance in an architecture-neutral, representative, and reproducible manner challenging. There is a clear need for industry-wide standard ML benchmarking and evaluation criteria. MLPerf Inference answers that call. In this paper, we present our benchmarking method for evaluating ML inference systems. Driven by more than 30 organizations as well as more than 200 ML engineers and practitioners, MLPerf prescribes a set of rules and best practices to ensure comparability across systems with wildly differing architectures. The first call for submissions garnered more than 600 reproducible inference-performance measurements from 14 organizations, representing over 30 systems that showcase a wide range of capabilities. The submissions attest to the benchmark's flexibility and adaptability. △ Less

Submitted 9 May, 2020; v1 submitted 6 November, 2019; originally announced November 2019.

Comments: ISCA 2020

MLPerf Training Benchmark

Authors: Peter Mattson, Christine Cheng, Cody Coleman, Greg Diamos, Paulius Micikevicius, David Patterson, Hanlin Tang, Gu-Yeon Wei, Peter Bailis, Victor Bittorf, David Brooks, Dehao Chen, Debojyoti Dutta, Udit Gupta, Kim Hazelwood, Andrew Hock, Xinyuan Huang, Atsushi Ike, Bill Jia, Daniel Kang, David Kanter, Naveen Kumar, Jeffery Liao, Guokai Ma, Deepak Narayanan , et al. (12 additional authors not shown)

Abstract: Machine learning (ML) needs industry-standard performance benchmarks to support design and competitive evaluation of the many emerging software and hardware solutions for ML. But ML training presents three unique benchmarking challenges absent from other domains: optimizations that improve training throughput can increase the time to solution, training is stochastic and time to solution exhibits h… ▽ More Machine learning (ML) needs industry-standard performance benchmarks to support design and competitive evaluation of the many emerging software and hardware solutions for ML. But ML training presents three unique benchmarking challenges absent from other domains: optimizations that improve training throughput can increase the time to solution, training is stochastic and time to solution exhibits high variance, and software and hardware systems are so diverse that fair benchmarking with the same binary, code, and even hyperparameters is difficult. We therefore present MLPerf, an ML benchmark that overcomes these challenges. Our analysis quantitatively evaluates MLPerf's efficacy at driving performance and scalability improvements across two rounds of results from multiple vendors. △ Less

Submitted 2 March, 2020; v1 submitted 2 October, 2019; originally announced October 2019.

Comments: MLSys 2020

Selection via Proxy: Efficient Data Selection for Deep Learning

Authors: Cody Coleman, Christopher Yeh, Stephen Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang, Jure Leskovec, Matei Zaharia

Abstract: Data selection methods, such as active learning and core-set selection, are useful tools for machine learning on large datasets. However, they can be prohibitively expensive to apply in deep learning because they depend on feature representations that need to be learned. In this work, we show that we can greatly improve the computational efficiency by using a small proxy model to perform data sele… ▽ More Data selection methods, such as active learning and core-set selection, are useful tools for machine learning on large datasets. However, they can be prohibitively expensive to apply in deep learning because they depend on feature representations that need to be learned. In this work, we show that we can greatly improve the computational efficiency by using a small proxy model to perform data selection (e.g., selecting data points to label for active learning). By removing hidden layers from the target model, using smaller architectures, and training for fewer epochs, we create proxies that are an order of magnitude faster to train. Although these small proxy models have higher error rates, we find that they empirically provide useful signals for data selection. We evaluate this "selection via proxy" (SVP) approach on several data selection tasks across five datasets: CIFAR10, CIFAR100, ImageNet, Amazon Review Polarity, and Amazon Review Full. For active learning, applying SVP can give an order of magnitude improvement in data selection runtime (i.e., the time it takes to repeatedly train and select points) without significantly increasing the final error (often within 0.1%). For core-set selection on CIFAR10, proxies that are over 10x faster to train than their larger, more accurate targets can remove up to 50% of the data without harming the final accuracy of the target, leading to a 1.6x end-to-end training time improvement. △ Less

Submitted 26 October, 2020; v1 submitted 26 June, 2019; originally announced June 2019.

Comments: ICLR 2020

Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark

Authors: Cody Coleman, Daniel Kang, Deepak Narayanan, Luigi Nardi, Tian Zhao, Jian Zhang, Peter Bailis, Kunle Olukotun, Chris Re, Matei Zaharia

Abstract: Researchers have proposed hardware, software, and algorithmic optimizations to improve the computational performance of deep learning. While some of these optimizations perform the same operations faster (e.g., increasing GPU clock speed), many others modify the semantics of the training procedure (e.g., reduced precision), and can impact the final model's accuracy on unseen data. Due to a lack of… ▽ More Researchers have proposed hardware, software, and algorithmic optimizations to improve the computational performance of deep learning. While some of these optimizations perform the same operations faster (e.g., increasing GPU clock speed), many others modify the semantics of the training procedure (e.g., reduced precision), and can impact the final model's accuracy on unseen data. Due to a lack of standard evaluation criteria that considers these trade-offs, it is difficult to directly compare these optimizations. To address this problem, we recently introduced DAWNBench, a benchmark competition focused on end-to-end training time to achieve near-state-of-the-art accuracy on an unseen dataset---a combined metric called time-to-accuracy (TTA). In this work, we analyze the entries from DAWNBench, which received optimized submissions from multiple industrial groups, to investigate the behavior of TTA as a metric as well as trends in the best-performing entries. We show that TTA has a low coefficient of variation and that models optimized for TTA generalize nearly as well as those trained using standard methods. Additionally, even though DAWNBench entries were able to train ImageNet models in under 3 minutes, we find they still underutilize hardware capabilities such as Tensor Cores. Furthermore, we find that distributed entries can spend more than half of their time on communication. We show similar findings with entries to the MLPERF v0.5 benchmark. △ Less

Submitted 1 December, 2019; v1 submitted 4 June, 2018; originally announced June 2018.

Open Set Intrusion Recognition for Fine-Grained Attack Categorization

Authors: Steve Cruz, Cora Coleman, Ethan M. Rudd, Terrance E. Boult

Abstract: Confidently distinguishing a malicious intrusion over a network is an important challenge. Most intrusion detection system evaluations have been performed in a closed set protocol in which only classes seen during training are considered during classification. Thus far, there has been no realistic application in which novel types of behaviors unseen at training -- unknown classes as it were -- mus… ▽ More Confidently distinguishing a malicious intrusion over a network is an important challenge. Most intrusion detection system evaluations have been performed in a closed set protocol in which only classes seen during training are considered during classification. Thus far, there has been no realistic application in which novel types of behaviors unseen at training -- unknown classes as it were -- must be recognized for manual categorization. This paper comparatively evaluates malware classification using both closed set and open set protocols for intrusion recognition on the KDDCUP'99 dataset. In contrast to much of the previous work, we employ a fine-grained recognition protocol, in which the dataset is loosely open set -- i.e., recognizing individual intrusion types -- e.g., "sendmail", "snmp guess", ..., etc., rather than more general attack categories (e.g., "DoS","Probe","R2L","U2R","Normal"). We also employ two different classifier types -- Gaussian RBF kernel SVMs, which are not theoretically guaranteed to bound open space risk, and W-SVMs, which are theoretically guaranteed to bound open space risk. We find that the W-SVM offers superior performance under the open set regime, particularly as the cost of misclassifying unknown classes at query time (i.e., classes not present in the training set) increases. Results of performance tradeoff with respect to cost of unknown as well as discussion of the ramifications of these findings in an operational setting are presented. △ Less

Submitted 7 March, 2017; originally announced March 2017.

Comments: Pre-print of camera-ready version to appear at the IEEE Homeland Security Technologies (HST) 2017 Conference