Get Started
Home
Topics
Search
Library
Research questionHow can biomedical question answering retrieve the right evidence and produce accurate answers?Biomedical QA must identify useful evidence from document collections and turn it into answers that remain accurate and grounded. Retrieval quality and answer quality are related but distinct parts of the problem.
AI
Evaluation & Benchmarks
Health
Information Retrieval
Multi-agent Systems
Natural Language Processing
Reasoning
Retrieval-Augmented Generation
Latest papersRecent research connected to this question, newest first.BIT.UA at BioASQ 14B: Modular Retrieval with pg_textsearch and Qdrant, and Agent-Based Answer GenerationThe evidence comes from the BioASQ 14B Task B setting, covering Phase A document retrieval, reranking, snippets, and Phases A+ and B answer generation. The reported pipeline uses BM25 and dense retrieval, HyDE-based expansion, reranker training with dense negatives, and multi-agent answer generation with an LLM judge; results are reported across BioASQ batches.research paper · Sep 4, 2026Multilingual Medical Reasoning for Question Answering with Large Language ModelsThe evidence covers 8B-parameter LLMs using reasoning traces generated with retrieval-augmented generation over medical Wikipedia. Evaluation uses MedQA and MedMCQA-derived datasets in English, Italian, and Spanish through few-shot prompting and supervised fine-tuning; released resources include traces, translated QA data, Medical-Wikipedia, and fine-tuned models.research paper · Sep 1, 2026
Related questions
How can structured RAG synthesize evidence scattered across many documents while limiting answer-generation cost?How can we compare medical VQA models when generation obscures answer signal and biases answer positions?How can table question answering choose between local and full-table context for each question?How should retrieval systems select passages that form coherent evidence chains for multi-hop questions?