activity
20202026
most citedTowards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions

1 citations · 3 across the 17 of their papers we have counts for

collaborators

24 papers

cs.MM2026

A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks

Ishani Mondal, Aparna Garimella, Ananya Sai +2

Automatically generated videos from scientific papers are increasingly used for education and research dissemination. However, existing evaluation metrics mainly measure visual qua…

cs.CL2026

An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA

Saransh Sharma, Pritika Ramu, Aparna Garimella +1

Answering open-ended questions remains challenging for AI systems because it requires synthesis, judgment, and exploration beyond factual retrieval, and users often refine answers…

cs.CL2026

Decisive: Guiding User Decisions with Optimal Preference Elicitation from Unstructured Documents

Akriti Jain, Anish Mulay, Divyansh Verma +3

Decision-making is a cognitively intensive task that requires synthesizing relevant information from multiple unstructured sources, weighing competing factors, and incorporating su…

cs.CL2025

Modeling Contextual Passage Utility for Multihop Question Answering

Akriti Jain, Aparna Garimella

Multihop Question Answering (QA) requires systems to identify and synthesize information from multiple text passages. While most prior retrieval methods assist in identifying relev…

cs.CL2025

TabReX : Tabular Referenceless eXplainable Evaluation

Tejas Anvekar, Junha Park, Aparna Garimella +1

Evaluating the quality of tables generated by large language models (LLMs) remains an open challenge: existing metrics either flatten tables into text, ignoring structure, or rely…

cs.CL2025

Knowing What's Missing: Assessing Information Sufficiency in Question Answering

Akriti Jain, Aparna Garimella

Determining whether a provided context contains sufficient information to answer a question is a critical challenge for building reliable question-answering systems. While simple p…