activity
20242026
collaborators

16 papers

cs.CL2026

Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"

Dhruv Madhwal, Lyuxin David Zhang, Dan Roth +2

Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typic…

cs.CL2026

CORE-T: COherent REtrieval of Tables for Text-to-SQL

Hassan Soliman, Vivek Gupta, Dan Roth +1

Realistic text-to-SQL workflows often require joining multiple tables. As a result, accurately retrieving the relevant set of tables becomes a key bottleneck for end-to-end perform…

cs.CL2026

InterChart: Benchmarking Visual Reasoning Across Decomposed and Distributed Chart Information

Anirudh Iyengar Kaniyar Narayana Iyengar, Srija Mukhopadhyay, Adnan Qidwai +3

We introduce InterChart, a diagnostic benchmark that evaluates how well vision-language models (VLMs) reason across multiple related charts, a task central to real-world applicatio…

cs.IR2026

SAGE: Structure Aware Graph Expansion for Retrieval of Heterogeneous Data

Prasham Titiya, Rohit Khoja, Tomer Wolfson +2

Retrieval-augmented question answering over heterogeneous corpora requires connected evidence across text, tables, and graph nodes. While entity-level knowledge graphs support stru…

cs.CL2025

Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering

Pragya Srivastava, Manuj Malik, Vivek Gupta +2

Large Language Models (LLMs), excel in natural language understanding, but their capability for complex mathematical reasoning with an amalgamation of structured tables and unstruc…

cs.AI2025

Weaver: Interweaving SQL and LLM for Table Reasoning

Rohit Khoja, Devanshu Gupta, Yanjie Fu +2

Querying tables with unstructured data is challenging due to the presence of text (or image), either embedded in the table or in external paragraphs, which traditional SQL struggle…