arXiv · cs.AI · Le Zhou, Xiao Luo, Chinmay Chandra, Zhan Zhang · 6 小时前模型评分34
小语言模型医疗问答微调研究:思维链(CoT,Chain of Thought) 与答案监督如何权衡
Balancing Chain-of-Thought and Answer Supervision for Small Language Models on Medical Question Answering
导读
一项研究比较了两种链式推理(思维链(CoT,Chain of Thought),Chain-of-Thought)监督微调方法在不超过 9B 参数小语言模型医疗问答上的表现:全序列等权(UaS)与分段加权(SwS)。
分类置信度
中 · 待人工复核
- 只有单一媒体来源,需要人工复核。
来源级别:媒体与个人
应用领域:医疗与生命科学
事件类型:研究发布
证据摘录
- “This paper compares two chain-of-thought (CoT) supervised fine-tuning methods: Uniform-across-Sequence (UaS), which applies equal loss weighting to the full CoT-and-answer sequence, and Segment-weighted (SwS), which separately weights CoT and answer losses.”
来源:arXiv · cs.AI · arxiv.org