works on

From the 1 of 11 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering

Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi +7

As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal…

cs.CL2026

Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations

Zichao Li, Gang Wu, Zichao Wang +5

Large language model agents operate in partially observable, long-horizon settings where obtaining supervision remains a major bottleneck. We address this by utilizing a source of…

cs.CL2026

Reasoning-Based Personalized Generation for Users with Sparse Data

Bo Ni, Branislav Kveton, Samyadeep Basu +14

Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history. However, real-world users usually possess sparse…

cs.CL2025

Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models

Sriram Balasubramanian, Samyadeep Basu, Koustava Goswami +6

Large language models (LLMs) are increasingly used for long-document question answering, where reliable attribution to sources is critical for trust. Existing post-hoc attribution…

cs.CL2025

On Mechanistic Circuits for Extractive Question-Answering

Samyadeep Basu, Vlad Morariu, Zichao Wang +4

Large language models are increasingly used to process documents and facilitate question-answering on them. In our paper, we extract mechanistic circuits for this real-world langua…

cs.CL2024

Persona-SQ: A Personalized Suggested Question Generation Framework For Real-world Documents

Zihao Lin, Zichao Wang, Yuanting Pan +5

Suggested questions (SQs) provide an effective initial interface for users to engage with their documents in AI-powered reading applications. In practical reading sessions, users h…