On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness
英文标题：On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness
arXiv:2607.29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought. This has been a promising development for AI safety--where models verbalize their reasoning, it is possible to monitor it. However, in some cases, models do not verbalize
打开原文相关 1.6 · 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:2607.29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought. This has been a promising development for AI safety--where models verbalize their reasoning, it is possible to monitor it. However, in some cases, models do not verbalize
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
×