arXiv cs.CL· Hanwen Zhang, Enyi Jiang, Ruike Zhu, Qinan Yu, Sanmi Koyejo·· 12 小时前AI 评分42
REACT：思维链轨迹的表征早期分析与控制
REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories
AI 导读
REACT 通过在早期 CoT 隐藏状态上施加一次条件激活干预来控制推理模型的安全轨迹，模型权重保持冻结、后续 token 不再修改。研究在三个蒸馏推理模型上发现最强增益集中在第 2-3 个 token 的早期窗口，DeepSeek-R1-Distill-Llama-8B 到第 4、5 个 token 时效果降至接近零。
正文 · 原文
Abstract:Chain-of-thought (CoT) generation offers an opportunity to intervene before a reasoning model completes its answer. But does the point at which risk is easiest to detect also offer the most effective control? We study this question with REACT, a conditional activation intervention that learns a safety direction from paired safe and unsafe trajectories and applies it once to an early CoT hidden state. The model weights remain frozen, and all subsequent tokens are generated without further edits. To study timing, we train directions separately at each of the first five CoT positions and evaluate ungated edits with full post-edit regeneration. Across three distilled reasoning models and three generation seeds, the strongest gains concentrate in a two- to three-token early window; on DeepSeek-R1-Distill-Llama-8B, the effect falls to approximately zero at the fourth and fifth tokens, even though later states can be more predictive of risk. This separates risk readability from effective control: intervention timing must be evaluated through its effect on subsequent generation. On the same 8B model, REACT raises the rate of fully safe CoT-answer outputs on StrongREJECT-273 from 29.06% to 82.05%, while keeping benign refusal and usefulness near baseline. An anonymized implementation is available at this https URL.
| Comments: | 26 pages, 2 figures |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.32113 [cs.LG] |
| (or arXiv:2610.32113v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32113 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hanwen Zhang [view email]
[v1]
Fri, 23 Oct 2026 03:28:34 UTC (155 KB)
来源：arXiv cs.CL · arxiv.org