6 papers
What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA
Yuelyu Ji, Min Gu Kwak, Hang Zhang +3
Medical RAG needs evidence-grounded claims, so plugging a claim-level NLI checker into retrieval-augmented RL is intuitive. \textbf{We find that the checker's \emph{output distribu…
Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning
Hang Zhang, Ruheng Wang, Yuelyu Ji +7
Large language models have achieved strong performance on medical reasoning benchmarks, yet their deployment in clinical settings demands rigorous verification to ensure factual ac…
MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented Generation
Yuelyu Ji, Min Gu Kwak, Hang Zhang +3
Biomedical retrieval-augmented generation (RAG) can ground LLM answers in medical literature, yet long-form outputs often contain isolated unsupported or contradictory claims with…
Orchestrator Multi-Agent Clinical Decision Support System for Secondary Headache Diagnosis in Primary Care
Xizhi Wu, Nelly Estefanie Garduno-Rapp, Justin F Rousseau +6
Unlike most primary headaches, secondary headaches need specialized care and can have devastating consequences if not treated promptly. Clinical guidelines highlight several 'red f…
DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QA
Yuelyu Ji, Hang Zhang, Shiven Verma +4
We propose DeepRAG, a novel framework that integrates DeepSeek hierarchical question decomposition capabilities with RAG Gym unified retrieval-augmented generation optimization usi…
Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systems
Yuelyu Ji, Hang Zhang, Yanshan Wang
Medical Question Answering systems based on Retrieval Augmented Generation is promising for clinical decision support because they can integrate external knowledge, thus reducing i…