11 papers
More Debate, Same Evidence: Structural Limits of Homogeneous Multi-Agent Groundedness
Yuelyu Ji
Large language model (LLM) judges are increasingly organized as multi-agent panels under the assumption that exchanging critiques improves judgment quality. We test this assumption…
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…
StepGap: A Hybrid NLI-LLM Checker for Step-Level Evidence-Gap Detectionin Multi-Hop Question Answering
Yuelyu Ji, Zhuochun Li, Hui Ji +1
We present \textbf{StepGap}, a hybrid NLI-LLM decision tree that detects step-level evidence gaps in multi-hop QA and emits one of three typed labels: \textsc{Contradicted Claim} (…
A Scoping Review of LLM-as-a-Judge in Healthcare and the MedJUDGE Framework
Chenyu Li, Zohaib Akhtar, Mingu Kwak +13
As large language models (LLMs) increasingly generate and process clinical text, scalable evaluation has become critical. LLM-as-a-Judge (LaaJ), which uses LLMs to evaluate model o…
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…
MRAG-Suite: A Diagnostic Evaluation Platform for Visual Retrieval-Augmented Generation
Yuelyu Ji, Wuwei Lan, Patrick NG
Multimodal Retrieval-Augmented Generation (Visual RAG) significantly advances question answering by integrating visual and textual evidence. Yet, current evaluations fail to system…