When Expert Disagreement Hurts: Prestige and Selectivity in LLM Decision Revision

研究论文 Hugging Face Papers 原文语言:中文

论文摘要(作者报告,未经本站复测):When language models revise a decision after another agent disagrees, neither reversal counts nor final accuracy shows whether they are fixing mistakes or abandoning correct answers.

原文摘录

论文摘要(作者报告,未经本站复测):When language models revise a decision after another agent disagrees, neither reversal counts nor final accuracy shows whether they are fixing mistakes or abandoning correct answers.

以下是来源提供的简短摘录,完整内容请查看原文。

参考来源

← 返回每日简报