Papers by Atharv Naphade
Rational Synthesizers or Heuristic Followers? Analyzing LLMs in RAG-based Question-Answering (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) is the prevailing paradigm for grounding Large Language Models. |
| Approach: | They propose a method to integrate conflicting retrieved evidence into large language models. |
| Outcome: | The proposed model is based on a curated dataset of 1,635 controversial questions paired with 15,058 diversely-sourced evidence documents. |