CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness
英文标题：CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness
arXiv:2607.18820v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning is widely used to improve both the performance and interpretability of large language models (LLMs), yet the generated reasoning may not faithfully support the final answer. We study this problem from a causal perspect
打开原文相关 2.4 · 机会 0
2.1 KB
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.18820v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning is widely used to improve both the performance and interpretability of large language models (LLMs), yet the generated reasoning may not faithfully support the final answer. We study this problem from a causal perspect
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×