一作ACL 2026Findings· Findings of ACL
TAGS : A Test-Time Generalist–Specialist Framework with Retrieval-Augmented Reasoning and Verification
Jianghao Wu · Feilong Tang · Yulong Li · Ming Hu · Haochen Xue · Shoaib Jameel · Zongyuan Ge · Yutong Xie · Imran Razzak
摘要
Recent advances such as Chain-of-Thought prompting have significantly improved large language models (LLMs) in zero-shot medical reasoning. However, prompting-based methods often remain shallow and unstable, while fine-tuned medical LLMs suffer from poor generalization under distribution shifts a...