Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict 文章

ArXiv CS.CL2026-05-28NEWSen作者: Pruthvinath Jeripity Venkata
查看原文 →
关系图谱

Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict · 相关技术

相关技术

ROUGE-Lintrospective faithfulnesschain-of-thought