指令微调对模型置信度与词汇多样性的影响研究

AI 摘要

该研究探讨了指令微调对模型置信度和词汇多样性的影响。研究发现，指令微调会改变模型的置信度，但不会改善校准，同时会降低推理的多样性。这些效应在控制答案选择和推理长度后依然存在，表明置信度和推理多样性捕捉了指令微调的不同影响。

正文节选

Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity Abstract Instruction tuning changes model confidence and reduces rationale diversity without improving calibration, indicating distinct effects on reasoning and certainty. Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recently been shown to exhibit verbalized overconfidence. In question answering, verbalized model overconfidence may be

发布时间：—

抓取时间：2026-08-14 16:55

来源机构：Hugging Face