Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering
少样本思维链推理以提示LLMs进行开放式医学问答
机构 * IBM Research(IBM研究院) ; Indian Institute of Technology Bombay(印度理工学院孟买分校)
AI总结 提出MEDQA-OPEN数据集和CLINICR提示方法,通过思维链推理提升LLMs在开放式医学问答中的表现,并引入奖励模型进行答案验证。
Comments The paper is accepted in EMNLP 2024 Findings