-
PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction
Authors:
Pirzada Suhail,
Nagasai Saketh Naidu,
Atanu R Sinha,
Amit Sethi
Abstract:
Large language models (LLMs) generate text by auto-regressively sampling the next token. This inherently leads to a many-to-many mapping between prompts and responses, complicating the task of inferring prompts from observed outputs. Prior work on LLM inversion frames prompt recovery as a semantic reconstruction task. They rely on fine-tuning pretrained sequence-to-sequence models on large externa…
▽ More
Large language models (LLMs) generate text by auto-regressively sampling the next token. This inherently leads to a many-to-many mapping between prompts and responses, complicating the task of inferring prompts from observed outputs. Prior work on LLM inversion frames prompt recovery as a semantic reconstruction task. They rely on fine-tuning pretrained sequence-to-sequence models on large external datasets--and requiring access to model weights or logits--to generate semantically plausible prompts. In contrast, we present a functional approach to inverting a given LLM in a black-box setting, without auxiliary aids. We train an explicit inverse language model entirely from scratch on data synthetically generated from the target LLM itself. Analogous to forward next-token prediction, our inverse model is trained using previous-token prediction, establishing a generative link between the forward and inverse processes that enables faithful prompt reconstruction. Moreover, it naturally supports diverse prompt reconstructions through sampling, whereby all such prompts induce similar responses under the forward, target LLM. Our approach generalises across datasets and exhibits transferability in reconstructing prompts from responses generated by different LLMs. Further, across the set of token based evaluation metrics for prompt and response reconstructions, our approach outperforms prior work.
△ Less
Submitted 31 July, 2026;
originally announced July 2026.
-
Subjective Behaviors and Preferences in LLM: Language of Browsing
Authors:
Sai Sundaresan,
Harshita Chopra,
Atanu R. Sinha,
Koustava Goswami,
Nagasai Saketh Naidu,
Raghav Karan,
N Anushka
Abstract:
A Large Language Model (LLM) offers versatility across domains and tasks, purportedly benefiting users with a wide variety of behaviors and preferences. We question this perception about an LLM when users have inherently subjective behaviors and preferences, as seen in their ubiquitous and idiosyncratic browsing of websites or apps. The sequential behavior logs of pages, thus generated, form somet…
▽ More
A Large Language Model (LLM) offers versatility across domains and tasks, purportedly benefiting users with a wide variety of behaviors and preferences. We question this perception about an LLM when users have inherently subjective behaviors and preferences, as seen in their ubiquitous and idiosyncratic browsing of websites or apps. The sequential behavior logs of pages, thus generated, form something akin to each user's self-constructed "language", albeit without the structure and grammar imbued in natural languages. We ask: (i) Can a small LM represent the "language of browsing" better than a large LM? (ii) Can an LM with a single set of parameters (or, single LM) adequately capture myriad users' heterogeneous, subjective behaviors and preferences? (iii) Can a single LM with high average performance, yield low variance in performance to make alignment good at user level? We introduce clusterwise LM training, HeTLM (Heterogeneity aware Training of Language Model), appropriate for subjective behaviors. We find that (i) a small LM trained using a page-level tokenizer outperforms large pretrained or finetuned LMs; (ii) HeTLM with heterogeneous cluster specific set of parameters outperforms a single LM of the same family, controlling for the number of parameters; and (iii) a higher mean and a lower variance in generation ensues, implying improved alignment.
△ Less
Submitted 18 September, 2025; v1 submitted 21 August, 2025;
originally announced August 2025.
-
Agentic Enterprise: AI-Centric User to User-Centric AI
Authors:
Arpit Narechania,
Alex Endert,
Atanu R Sinha
Abstract:
After a very long winter, the Artificial Intelligence (AI) spring is here. Or, so it seems over the last three years. AI has the potential to impact many areas of human life - personal, social, health, education, professional. In this paper, we take a closer look at the potential of AI for Enterprises, where decision-making plays a crucial and repeated role across functions, tasks, and operations.…
▽ More
After a very long winter, the Artificial Intelligence (AI) spring is here. Or, so it seems over the last three years. AI has the potential to impact many areas of human life - personal, social, health, education, professional. In this paper, we take a closer look at the potential of AI for Enterprises, where decision-making plays a crucial and repeated role across functions, tasks, and operations. We consider Agents imbued with AI as means to increase decision-productivity of enterprises. We highlight six tenets for Agentic success in enterprises, by drawing attention to what the current, AI-Centric User paradigm misses, in the face of persistent needs of and usefulness for Enterprise Decision-Making. In underscoring a shift to User-Centric AI, we offer six tenets and promote market mechanisms for platforms, aligning the design of AI and its delivery by Agents to the cause of enterprise users.
△ Less
Submitted 28 June, 2025;
originally announced June 2025.
-
Sequential Causal Discovery with Noisy Language Model Priors
Authors:
Prakhar Verma,
David Arbour,
Sunav Choudhary,
Harshita Chopra,
Arno Solin,
Atanu R. Sinha
Abstract:
Causal discovery from observational data typically assumes access to complete data and availability of perfect domain experts. In practice, data often arrive in batches, are subject to sampling bias, and expert knowledge is scarce. Language Models (LMs) offer a surrogate for expert knowledge but suffer from hallucinations, inconsistencies, and bias. We present a hybrid framework that bridges these…
▽ More
Causal discovery from observational data typically assumes access to complete data and availability of perfect domain experts. In practice, data often arrive in batches, are subject to sampling bias, and expert knowledge is scarce. Language Models (LMs) offer a surrogate for expert knowledge but suffer from hallucinations, inconsistencies, and bias. We present a hybrid framework that bridges these gaps by adaptively integrating sequential batch data with LM-derived noisy, expert knowledge while accounting for both data-induced and LM-induced biases. We propose a representation shift from Directed Acyclic Graph (DAG) to Partial Ancestral Graph (PAG), that accommodates ambiguities within a coherent framework, allowing grounding the global LM knowledge in local observational data. To guide LM interactions, we use a sequential optimization scheme that adaptively queries the most informative edges. Across varied datasets and LMs, we outperform prior work in structural accuracy and extend to parameter estimation, showing robustness to LM noise.
△ Less
Submitted 8 May, 2026; v1 submitted 19 June, 2025;
originally announced June 2025.
-
Guidance Source Matters: How Guidance from AI, Expert, or a Group of Analysts Impacts Visual Data Preparation and Analysis
Authors:
Arpit Narechania,
Alex Endert,
Atanu R Sinha
Abstract:
The progress in generative AI has fueled AI-powered tools like co-pilots and assistants to provision better guidance, particularly during data analysis. However, research on guidance has not yet examined the perceived efficacy of the source from which guidance is offered and the impact of this source on the user's perception and usage of guidance. We ask whether users perceive all guidance sources…
▽ More
The progress in generative AI has fueled AI-powered tools like co-pilots and assistants to provision better guidance, particularly during data analysis. However, research on guidance has not yet examined the perceived efficacy of the source from which guidance is offered and the impact of this source on the user's perception and usage of guidance. We ask whether users perceive all guidance sources as equal, with particular interest in three sources: (i) AI, (ii) human expert, and (iii) a group of human analysts. As a benchmark, we consider a fourth source, (iv) unattributed guidance, where guidance is provided without attribution to any source, enabling isolation of and comparison with the effects of source-specific guidance. We design a five-condition between-subjects study, with one condition for each of the four guidance sources and an additional (v) no-guidance condition, which serves as a baseline to evaluate the influence of any kind of guidance. We situate our study in a custom data preparation and analysis tool wherein we task users to select relevant attributes from an unfamiliar dataset to inform a business report. Depending on the assigned condition, users can request guidance, which the system then provides in the form of attribute suggestions. To ensure internal validity, we control for the quality of guidance across source-conditions. Through several metrics of usage and perception, we statistically test five preregistered hypotheses and report on additional analysis. We find that the source of guidance matters to users, but not in a manner that matches received wisdom. For instance, users utilize guidance differently at various stages of analysis, including expressing varying levels of regret, despite receiving guidance of similar quality. Notably, users in the AI condition reported both higher post-task benefit and regret.
△ Less
Submitted 2 February, 2025;
originally announced February 2025.
-
Fundamental Limits of Throughput and Availability: Applications to prophet inequalities & transaction fee mechanism design
Authors:
Aadityan Ganesh,
Jason Hartline,
Atanu R Sinha,
Matthew vonAllmen
Abstract:
This paper studies the fundamental limits of availability and throughput for independent and heterogeneous demands of a limited resource. Availability is the probability that the demands are below the capacity of the resource. Throughput is the expected fraction of the resource that is utilized by the demands. We offer a concentration inequality generator that gives lower bounds on feasible availa…
▽ More
This paper studies the fundamental limits of availability and throughput for independent and heterogeneous demands of a limited resource. Availability is the probability that the demands are below the capacity of the resource. Throughput is the expected fraction of the resource that is utilized by the demands. We offer a concentration inequality generator that gives lower bounds on feasible availability and throughput pairs with a given capacity and independent but not necessarily identical distributions of up-to-unit demands. We show that availability and throughput cannot both be poor. These bounds are analogous to tail inequalities on sums of independent random variables, but hold throughout the support of the demand distribution. This analysis gives analytically tractable bounds supporting the unit-demand characterization of Chawla, Devanur, and Lykouris (2023) and generalizes to up-to-unit demands. Our bounds also provide an approach towards improved multi-unit prophet inequalities (Hajiaghayi, Kleinberg, and Sandholm, 2007). They have applications to transaction fee mechanism design (for blockchains) where high availability limits the probability of profitable user-miner coalitions (Chung and Shi, 2023).
△ Less
Submitted 14 July, 2024; v1 submitted 29 February, 2024;
originally announced February 2024.
-
Delivery Optimized Discovery in Behavioral User Segmentation under Budget Constraint
Authors:
Harshita Chopra,
Atanu R. Sinha,
Sunav Choudhary,
Ryan A. Rossi,
Paavan Kumar Indela,
Veda Pranav Parwatala,
Srinjayee Paul,
Aurghya Maiti
Abstract:
Users' behavioral footprints online enable firms to discover behavior-based user segments (or, segments) and deliver segment specific messages to users. Following the discovery of segments, delivery of messages to users through preferred media channels like Facebook and Google can be challenging, as only a portion of users in a behavior segment find match in a medium, and only a fraction of those…
▽ More
Users' behavioral footprints online enable firms to discover behavior-based user segments (or, segments) and deliver segment specific messages to users. Following the discovery of segments, delivery of messages to users through preferred media channels like Facebook and Google can be challenging, as only a portion of users in a behavior segment find match in a medium, and only a fraction of those matched actually see the message (exposure). Even high quality discovery becomes futile when delivery fails. Many sophisticated algorithms exist for discovering behavioral segments; however, these ignore the delivery component. The problem is compounded because (i) the discovery is performed on the behavior data space in firms' data (e.g., user clicks), while the delivery is predicated on the static data space (e.g., geo, age) as defined by media; and (ii) firms work under budget constraint. We introduce a stochastic optimization based algorithm for delivery optimized discovery of behavioral user segmentation and offer new metrics to address the joint optimization. We leverage optimization under a budget constraint for delivery combined with a learning-based component for discovery. Extensive experiments on a public dataset from Google and a proprietary dataset show the effectiveness of our approach by simultaneously improving delivery metrics, reducing budget spend and achieving strong predictive performance in discovery.
△ Less
Submitted 15 March, 2024; v1 submitted 4 February, 2024;
originally announced February 2024.
-
Learning to Infer Unobserved Behaviors: Estimating User's Preference for a Site over Other Sites
Authors:
Atanu R Sinha,
Tanay Anand,
Paridhi Maheshwari,
A V Lakshmy,
Vishal Jain
Abstract:
A site's recommendation system relies on knowledge of its users' preferences to offer relevant recommendations to them. These preferences are for attributes that comprise items and content shown on the site, and are estimated from the data of users' interactions with the site. Another form of users' preferences is material too, namely, users' preferences for the site over other sites, since that s…
▽ More
A site's recommendation system relies on knowledge of its users' preferences to offer relevant recommendations to them. These preferences are for attributes that comprise items and content shown on the site, and are estimated from the data of users' interactions with the site. Another form of users' preferences is material too, namely, users' preferences for the site over other sites, since that shows users' base level propensities to engage with the site. Estimating users' preferences for the site, however, faces major obstacles because (a) the focal site usually has no data of its users' interactions with other sites; these interactions are users' unobserved behaviors for the focal site; and (b) the Machine Learning literature in recommendation does not offer a model of this situation. Even if (b) is resolved, the problem in (a) persists since without access to data of its users' interactions with other sites, there is no ground truth for evaluation. Moreover, it is most useful when (c) users' preferences for the site can be estimated at the individual level, since the site can then personalize recommendations to individual users. We offer a method to estimate individual user's preference for a focal site, under this premise. In particular, we compute the focal site's share of a user's online engagements without any data from other sites. We show an evaluation framework for the model using only the focal site's data, allowing the site to test the model. We rely upon a Hierarchical Bayes Method and perform estimation in two different ways - Markov Chain Monte Carlo and Stochastic Gradient with Langevin Dynamics. Our results find good support for the approach to computing personalized share of engagement and for its evaluation.
△ Less
Submitted 15 December, 2023;
originally announced December 2023.
-
DataPilot: Utilizing Quality and Usage Information for Subset Selection during Visual Data Preparation
Authors:
Arpit Narechania,
Fan Du,
Atanu R Sinha,
Ryan A. Rossi,
Jane Hoffswell,
Shunan Guo,
Eunyee Koh,
Shamkant B. Navathe,
Alex Endert
Abstract:
Selecting relevant data subsets from large, unfamiliar datasets can be difficult. We address this challenge by modeling and visualizing two kinds of auxiliary information: (1) quality - the validity and appropriateness of data required to perform certain analytical tasks; and (2) usage - the historical utilization characteristics of data across multiple users. Through a design study with 14 data w…
▽ More
Selecting relevant data subsets from large, unfamiliar datasets can be difficult. We address this challenge by modeling and visualizing two kinds of auxiliary information: (1) quality - the validity and appropriateness of data required to perform certain analytical tasks; and (2) usage - the historical utilization characteristics of data across multiple users. Through a design study with 14 data workers, we integrate this information into a visual data preparation and analysis tool, DataPilot. DataPilot presents visual cues about "the good, the bad, and the ugly" aspects of data and provides graphical user interface controls as interaction affordances, guiding users to perform subset selection. Through a study with 36 participants, we investigate how DataPilot helps users navigate a large, unfamiliar tabular dataset, prepare a relevant subset, and build a visualization dashboard. We find that users selected smaller, effective subsets with higher quality and usage, and with greater success and confidence.
△ Less
Submitted 2 March, 2023;
originally announced March 2023.
-
B2B Advertising: Joint Dynamic Scoring of Account and Users
Authors:
Atanu R. Sinha,
Gautam Choudhary,
Mansi Agarwal,
Shivansh Bindal,
Abhishek Pande,
Camille Girabawe
Abstract:
When a business sells to another business (B2B), the buying business is represented by a group of individuals, termed account, who collectively decide whether to buy. The seller advertises to each individual and interacts with them, mostly by digital means. The sales cycle is long, most often over a few months. There is heterogeneity among individuals belonging to an account in seeking information…
▽ More
When a business sells to another business (B2B), the buying business is represented by a group of individuals, termed account, who collectively decide whether to buy. The seller advertises to each individual and interacts with them, mostly by digital means. The sales cycle is long, most often over a few months. There is heterogeneity among individuals belonging to an account in seeking information and hence the seller needs to score the interest of each individual over a long horizon to decide which individuals must be reached and when. Moreover, the buy decision rests with the account and must be scored to project the likelihood of purchase, a decision that is subject to change all the way up to the actual decision, emblematic of group decision making. We score decision of the account and its individuals in a dynamic manner. Dynamic scoring allows opportunity to influence different individual members at different time points over the long horizon. The dataset contains behavior logs of each individual's communication activities with the seller; but, there are no data on consultations among individuals which result in the decision. Using neural network architecture, we propose several ways to aggregate information from individual members' activities, to predict the group's collective decision. Multiple evaluations find strong model performance.
△ Less
Submitted 28 September, 2022;
originally announced September 2022.
-
Personalized Detection of Cognitive Biases in Actions of Users from Their Logs: Anchoring and Recency Biases
Authors:
Atanu R Sinha,
Navita Goyal,
Sunny Dhamnani,
Tanay Asija,
Raja K Dubey,
M V Kaarthik Raja,
Georgios Theocharous
Abstract:
Cognitive biases are mental shortcuts humans use in dealing with information and the environment, and which result in biased actions and behaviors (or, actions), unbeknownst to themselves. Biases take many forms, with cognitive biases occupying a central role that inflicts fairness, accountability, transparency, ethics, law, medicine, and discrimination. Detection of biases is considered a necessa…
▽ More
Cognitive biases are mental shortcuts humans use in dealing with information and the environment, and which result in biased actions and behaviors (or, actions), unbeknownst to themselves. Biases take many forms, with cognitive biases occupying a central role that inflicts fairness, accountability, transparency, ethics, law, medicine, and discrimination. Detection of biases is considered a necessary step toward their mitigation. Herein, we focus on two cognitive biases - anchoring and recency. The recognition of cognitive bias in computer science is largely in the domain of information retrieval, and bias is identified at an aggregate level with the help of annotated data. Proposing a different direction for bias detection, we offer a principled approach along with Machine Learning to detect these two cognitive biases from Web logs of users' actions. Our individual user level detection makes it truly personalized, and does not rely on annotated data. Instead, we start with two basic principles established in cognitive psychology, use modified training of an attention network, and interpret attention weights in a novel way according to those principles, to infer and distinguish between these two biases. The personalized approach allows detection for specific users who are susceptible to these biases when performing their tasks, and can help build awareness among them so as to undertake bias mitigation.
△ Less
Submitted 1 July, 2022; v1 submitted 30 June, 2022;
originally announced June 2022.
-
Surveys without Questions: A Reinforcement Learning Approach
Authors:
Atanu R Sinha,
Deepali Jain,
Nikhil Sheoran,
Sopan Khosla,
Reshmi Sasidharan
Abstract:
The 'old world' instrument, survey, remains a tool of choice for firms to obtain ratings of satisfaction and experience that customers realize while interacting online with firms. While avenues for survey have evolved from emails and links to pop-ups while browsing, the deficiencies persist. These include - reliance on ratings of very few respondents to infer about all customers' online interactio…
▽ More
The 'old world' instrument, survey, remains a tool of choice for firms to obtain ratings of satisfaction and experience that customers realize while interacting online with firms. While avenues for survey have evolved from emails and links to pop-ups while browsing, the deficiencies persist. These include - reliance on ratings of very few respondents to infer about all customers' online interactions; failing to capture a customer's interactions over time since the rating is a one-time snapshot; and inability to tie back customers' ratings to specific interactions because ratings provided relate to all interactions. To overcome these deficiencies we extract proxy ratings from clickstream data, typically collected for every customer's online interactions, by developing an approach based on Reinforcement Learning (RL). We introduce a new way to interpret values generated by the value function of RL, as proxy ratings. Our approach does not need any survey data for training. Yet, on validation against actual survey data, proxy ratings yield reasonable performance results. Additionally, we offer a new way to draw insights from values of the value function, which allow associating specific interactions to their proxy ratings. We introduce two new metrics to represent ratings - one, customer-level and the other, aggregate-level for click actions across customers. Both are defined around proportion of all pairwise, successive actions that show increase in proxy ratings. This intuitive customer-level metric enables gauging the dynamics of ratings over time and is a better predictor of purchase than customer ratings from survey. The aggregate-level metric allows pinpointing actions that help or hurt experience. In sum, proxy ratings computed unobtrusively from clickstream, for every action, for each customer, and for every session can offer interpretable and more insightful alternative to surveys.
△ Less
Submitted 11 June, 2020;
originally announced June 2020.
-
An RNN-Survival Model to Decide Email Send Times
Authors:
Harvineet Singh,
Moumita Sinha,
Atanu R. Sinha,
Sahil Garg,
Neha Banerjee
Abstract:
Email communications are ubiquitous. Firms control send times of emails and thereby the instants at which emails reach recipients (it is assumed email is received instantaneously from the send time). However, they do not control the duration it takes for recipients to open emails, labeled as time-to-open. Importantly, among emails that are opened, most occur within a short window from their send t…
▽ More
Email communications are ubiquitous. Firms control send times of emails and thereby the instants at which emails reach recipients (it is assumed email is received instantaneously from the send time). However, they do not control the duration it takes for recipients to open emails, labeled as time-to-open. Importantly, among emails that are opened, most occur within a short window from their send times. We posit that emails are likely to be opened sooner when send times are convenient for recipients, while for other send times, emails can get ignored. Thus, to compute appropriate send times it is important to predict times-to-open accurately. We propose a recurrent neural network (RNN) in a survival model framework to predict times-to-open, for each recipient. Using that we compute appropriate send times. We experiment on a data set of emails sent to a million customers over five months. The sequence of emails received by a person from a sender is a result of interactions with past emails from the sender, and hence contain useful signal that inform our model. This sequential dependence affords our proposed RNN-Survival (RNN-S) approach to outperform survival analysis approaches in predicting times-to-open. We show that best times to send emails can be computed accurately from predicted times-to-open. This approach allows a firm to tune send times of emails, which is in its control, to favorably influence open rates and engagement.
△ Less
Submitted 21 April, 2020;
originally announced April 2020.
-
Forecasting Granular Audience Size for Online Advertising
Authors:
Ritwik Sinha,
Dhruv Singal,
Pranav Maneriker,
Kushal Chawla,
Yash Shrivastava,
Deepak Pai,
Atanu R Sinha
Abstract:
Orchestration of campaigns for online display advertising requires marketers to forecast audience size at the granularity of specific attributes of web traffic, characterized by the categorical nature of all attributes (e.g. {US, Chrome, Mobile}). With each attribute taking many values, the very large attribute combination set makes estimating audience size for any specific attribute combination c…
▽ More
Orchestration of campaigns for online display advertising requires marketers to forecast audience size at the granularity of specific attributes of web traffic, characterized by the categorical nature of all attributes (e.g. {US, Chrome, Mobile}). With each attribute taking many values, the very large attribute combination set makes estimating audience size for any specific attribute combination challenging. We modify Eclat, a frequent itemset mining (FIM) algorithm, to accommodate categorical variables. For consequent frequent and infrequent itemsets, we then provide forecasts using time series analysis with conditional probabilities to aid approximation. An extensive simulation, based on typical characteristics of audience data, is built to stress test our modified-FIM approach. In two real datasets, comparison with baselines including neural network models, shows that our method lowers computation time of FIM for categorical data. On hold out samples we show that the proposed forecasting method outperforms these baselines.
△ Less
Submitted 8 January, 2019;
originally announced January 2019.