跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24598 · v1

Chain-of-Thought Hidden States Reveal Task-Solving Directions for Direct Answers

首次提交 2026-11-18 23:25
版本更新 2026-11-18 23:25
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

Chain-of-Thought (CoT) prompting improves the performance of Large Language Models by eliciting intermediate reasoning steps. However, CoT is far from perfect: on some tasks, models perform worse than with direct-answer prompting, and on others they generate a few hundred tokens to reach the correct answer. We start by labelling each CoT hidden state as recovering if patching it into the direct prompt yields the correct answer, and failed otherwise. A linear probe shows that the model encodes these two classes differently. We then show that the representation space of the direct prompt holds a direction for each question that leads the model, in a short generation, to the correct answer more often than CoT does. Specifically, we rotate the direct prompt's last hidden state once, before generation, towards a direction built for each question from its own recovering and failed states. Across 25 tasks, these directions raise the direct prompt's mean accuracy from 46%46\% to 85%85\% on LLaMA 3.1 8B (CoT: 69%69\%) and from 52%52\% to 86%86\% on Qwen 2.5 7B (CoT: 77%77\%), with a tenth of CoT's tokens. CoT is thus not the shortest route to this accuracy, and these directions can be used in future work to train models to align their states with them.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 23:25 · 最新观测版本

Chain-of-Thought Hidden States Reveal Task-Solving Directions for Direct Answers

Chain-of-Thought (CoT) prompting improves the performance of Large Language Models by eliciting intermediate reasoning steps. However, CoT is far from perfect: on some tasks, models perform worse than with direct-answer prompting, and on others they generate a few hundred tokens to reach the correct answer. We start by labelling each CoT hidden state as recovering if patching it into the direct prompt yields the correct answer, and failed otherwise. A linear probe shows that the model encodes these two classes differently. We then show that the representation space of the direct prompt holds a direction for each question that leads the model, in a short generation, to the correct answer more often than CoT does. Specifically, we rotate the direct prompt's last hidden state once, before generation, towards a direction built for each question from its own recovering and failed states. Across 25 tasks, these directions raise the direct prompt's mean accuracy from 46%46\% to 85%85\% on LLaMA 3.1 8B (CoT: 69%69\%) and from 52%52\% to 86%86\% on Qwen 2.5 7B (CoT: 77%77\%), with a tenth of CoT's tokens. CoT is thus not the shortest route to this accuracy, and these directions can be used in future work to train models to align their states with them.

查看此版本解读 →查看此版本原文 ↗