Papers by Fabricio Murai

1 papers
PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to QA provide inaccurate answers but lack mechanisms to iteratively refine poor queries.
Approach: They propose a biomedical question answering agent that performs self-critic query refinement . they propose re-reflection methods that kick in only after full retrieval is completed .
Outcome: a biomedical question answering agent achieves 78.32% accuracy on PubMedQA . the proposed approach provides practical assistance to clinicians and biomedically researchers .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations