5 papers
PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus
Gen Li, Yuanze Hu, Zhichao Yang +10
Clinical diagnosis requires flexible use of multiple reasoning paradigms under incomplete patient information. Existing LLM-based medical agents show strong medical reasoning abili…
MedFabric and EtHER: A Data-Centric Framework for Word-Level Fabrication Generation and Detection in Medical LLMs
Tung Sum Thomas Kwok, Qian Qian, Xiaofeng Lin +8
Large Language Models exhibit strong reasoning and semantic understanding capabilities but often hallucinate in domains that require expert knowledge, among which fabrications, the…
MedicalBench: Evaluating Large Language Models Toward Improved Medical Concept Extraction
Zhichao Yang, Gregory D. Lyng, Sanjit Singh Batra +1
Medical concept extraction from electronic health records underpins many downstream applications, yet remains challenging because medically meaningful concepts are frequently impli…
Fast and Effective On-policy Distillation from Reasoning Prefixes
Dongxu Zhang, Zhichao Yang, Sepehr Janghorbani +6
On-policy distillation (OPD), which samples trajectories from the student model and supervises them with a teacher at the token level, avoids relying solely on verifiable terminal…
Health-SCORE: Towards Scalable Rubrics for Improving Health-LLMs
Zhichao Yang, Sepehr Janghorbani, Dongxu Zhang +6
Rubrics are essential for evaluating open-ended LLM responses, especially in safety-critical domains such as healthcare. However, creating high-quality and domain-specific rubrics…