arXiv cs.CL· Zinan Tang, Zhuoshi Pan, Kairui Chen, Ze Yan, Shaomian Zheng, Yukun Zhang, Gang Wang, Biqing Huang·· 2 天前AI 评分25
CoTranslator：将反向 CoT 翻译为正向 CoT 的推理蒸馏方法
CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation
AI 导读
CoTranslator 通过将反向 CoT 响应翻译为经过验证的正向响应分布，实现高效推理蒸馏。在六个数学基准上，它比语义抑制方法平均准确率最高提升 5.82 个百分点；对两个 4B 学生模型，以 35.9% 的估算算力保留了拒绝采样 95.0% 的平均准确率。
正文 · 原文
Abstract:Reasoning distillation requires chain-of-thought (CoT) data with correct answers, but obtaining such data efficiently remains challenging. Forward CoT generation (FCG) followed by rejection sampling (RS) produces verified, question-only responses, yet may require many teacher calls for difficult problems. Reverse CoT generation (RCG) is cheaper because it conditions on the known answer, but access to this answer can lead to post-hoc rationalization and a mismatch with the student's answer-free inference setting. We propose CoTranslator, which learns to translate reverse CoT responses toward the distribution of verified forward responses. Trained on a small set of paired reverse and rejection-sampled forward responses, it supports large-scale generation and verification of student training data. Across six student models evaluated on six mathematics benchmarks, CoTranslator improves average accuracy over semantic suppression by up to $5.82$ percentage points. For two 4B students, it retains $95.0\%$ of rejection sampling's average accuracy while using $35.9\%$ of its estimated compute. Without retraining, the same translator transfers to a new mathematics dataset, a different teacher, and STEM problems, improving average STEM accuracy by $4.88$ and $4.31$ percentage points for 4B and 8B students, respectively. These results show that CoTranslator offers an efficient and transferable approach to reasoning distillation.
| Comments: | 18 pages, 12 figures, under review |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.20828 [cs.CL] |
| (or arXiv:2610.20828v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20828 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zinan Tang [view email]
[v1]
Wed, 14 Oct 2026 19:15:36 UTC (419 KB)
来源：arXiv cs.CL · arxiv.org