33 citations · 104 across the 21 of their papers we have counts for
21 papers
RAWR: Reward Assignment Without Rollouts in Verifiable Domains
Corentin Royer, Debarun Bhattacharjya, Anna Hedström +3
Understanding and evaluating multi-step reasoning in LLMs at the level of individual steps remains a key challenge. Process reward models (PRMs) provide a solution by scoring each…
SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models
Debarun Bhattacharjya, Balaji Ganesan, Junkyu Lee +4
When does a large language model (LLM) know what it does not know? Uncertainty quantification (UQ) provides measures of uncertainty, such as an estimate of the confidence in an LLM…
QueryGym: Step-by-Step Interaction with Relational Databases
Haritha Ananthakrishnan, Harsha Kokel, Kelsey Sikes +4
We introduce QueryGym, an interactive environment for building, testing, and evaluating LLM-based query planning agents. Existing frameworks often tie agents to specific query lang…
What Would an LLM Do? Evaluating Large Language Models for Policymaking to Alleviate Homelessness
Pierre Le Coz, Jia An Liu, Debarun Bhattacharjya +2
Large language models (LLMs) are increasingly being adopted in high-stakes domains. Their potential to encode evolving social contexts and to generate plausible scenarios position…
The Consistency Hypothesis in Uncertainty Quantification for Large Language Models
Quan Xiao, Debarun Bhattacharjya, Balaji Ganesan +5
Estimating the confidence of large language model (LLM) outputs is essential for real-world applications requiring high user trust. Black-box uncertainty quantification (UQ) method…
Knowledge Base Construction for Knowledge-Augmented Text-to-SQL
Jinheon Baek, Horst Samulowitz, Oktie Hassanzadeh +4
Text-to-SQL aims to translate natural language queries into SQL statements, which is practical as it enables anyone to easily retrieve the desired information from databases. Recen…
Q-function Decomposition with Intervention Semantics with Factored Action Spaces
Junkyu Lee, Tian Gao, Elliot Nelson +3
Many practical reinforcement learning environments have a discrete factored action space that induces a large combinatorial set of actions, thereby posing significant challenges. E…
FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models
Radu Marinescu, Debarun Bhattacharjya, Junkyu Lee +5
Large language models (LLMs) have achieved remarkable success in generative tasks, yet they often fall short in ensuring the factual accuracy of their outputs, thus limiting their…
Foundation Model Sherpas: Guiding Foundation Models through Knowledge and Reasoning
Debarun Bhattacharjya, Junkyu Lee, Don Joven Agravante +2
Foundation models (FMs) such as large language models have revolutionized the field of AI by showing remarkable performance in various tasks. However, they exhibit numerous limitat…
Self-Supervised Contrastive Pre-Training for Multivariate Point Processes
Xiao Shou, Dharmashankar Subramanian, Debarun Bhattacharjya +2
Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, b…
Distilling Event Sequence Knowledge From Large Language Models
Somin Wadhwa, Oktie Hassanzadeh, Debarun Bhattacharjya +2
Event sequence models have been found to be highly effective in the analysis and prediction of events. Building such models requires availability of abundant high-quality event seq…
Event Prediction using Case-Based Reasoning over Knowledge Graphs
Sola Shirai, Debarun Bhattacharjya, Oktie Hassanzadeh
Applying link prediction (LP) methods over knowledge graphs (KG) for tasks such as causal event prediction presents an exciting opportunity. However, typical LP models are ill-suit…
Summary Markov Models for Event Sequences
Debarun Bhattacharjya, Saurabh Sihag, Oktie Hassanzadeh +1
Datasets involving sequences of different types of events without meaningful time stamps are prevalent in many applications, for instance when extracted from textual corpora. We pr…
Logical Credal Networks
Haifeng Qian, Radu Marinescu, Alexander Gray +5
This paper introduces Logical Credal Networks, an expressive probabilistic logic that generalizes many prior models that combine logic and probability. Given imprecise information…
A Multi-Channel Neural Graphical Event Model with Negative Evidence
Tian Gao, Dharmashankar Subramanian, Karthikeyan Shanmugam +2
Event datasets are sequences of events of various types occurring irregularly over the time-line, and they are increasingly prevalent in numerous domains. Existing work for modelin…
Nonparametric estimation of utility functions
Mengyang Gu, Debarun Bhattacharjya, Dharmashankar Subramanian
Inferring a decision maker's utility function typically involves an elicitation phase where the decision maker responds to a series of elicitation queries, followed by an estimatio…
A Big Data Approach to Computational Creativity
Lav R. Varshney, Florian Pinel, Kush R. Varshney +3
Computational creativity is an emerging branch of artificial intelligence that places computers in the center of the creative process. Broadly, creativity involves a generative ste…
Evaluating influence diagrams with decision circuits
Debarun Bhattacharjya, Ross D. Shachter
Although a number of related algorithms have been developed to evaluate influence diagrams, exploiting the conditional independence in the diagram, the exact solution has remained…
Sensitivity analysis in decision circuits
Debarun Bhattacharjya, Ross D. Shachter
Decision circuits have been developed to perform efficient evaluation of influence diagrams [Bhattacharjya and Shachter, 2007], building on the advances in arithmetic circuits for…
Dynamic programming in in uence diagrams with decision circuits
Ross D. Shachter, Debarun Bhattacharjya
Decision circuits perform efficient evaluation of influence diagrams, building on the ad- vances in arithmetic circuits for belief net- work inference [Darwiche, 2003; Bhattachar-…
Three new sensitivity analysis methods for influence diagrams
Debarun Bhattacharjya, Ross D. Shachter
Performing sensitivity analysis for influence diagrams using the decision circuit framework is particularly convenient, since the partial derivatives with respect to every paramete…