让模型学会自我验证，有效减少冗余推理步骤。
VeriThinker: Learning to Verify Makes Reasoning Model Efficient
- 通过验证任务训练模型判断推理是否合理，抑制过度思考。
- 在MATH500上推理令牌减少44%，准确率提升0.8%。
- 适用于零样本推测性推理，适合追求高效推理的场景。
大型推理模型（LRMs）在复杂任务中表现优异，依赖思维链（CoT）推理。但其容易陷入过度思考，导致推理链条过长，显著增加推理开销。为解决此问题，我们提出VeriThinker，一种新型的CoT压缩方法。不同于传统直接用简化版CoT数据微调模型的方式，我们创新性地仅通过辅助验证任务进行微调：让模型学习准确判断CoT解法的正确性。这使模型更善于判断后续反思步骤是否必要，从而有效抑制过度思考。大量实验表明，VeriThinker显著缩短推理链长度，同时保持或略微提升准确率。应用于DeepSeek-R1-Distill-Qwen-7B时，在MATH500上推理令牌从3790降至2125（减少44%），准确率由94.0%提升至94.8%；在AIME25上，令牌从14321降至10287（减少28.2%），准确率由38.7%提升至40.8%。此外，实验还证明VeriThinker可实现零样本泛化至推测性推理。代码已开源。
原文摘要 · Abstract (English)
Large Reasoning Models (LRMs) excel at complex tasks using Chain-of-Thought (CoT) reasoning. However, their tendency to overthinking leads to unnecessarily lengthy reasoning chains, dramatically increasing inference costs. To mitigate this issue, we introduce VeriThinker, a novel approach for CoT compression. Unlike conventional methods that fine-tune LRMs directly on the original reasoning task using synthetic concise CoT data, we innovatively fine-tune the model solely through an auxiliary verification task. By training LRMs to accurately verify the correctness of CoT solutions, the LRMs inherently become more discerning about the necessity of subsequent self-reflection steps, thereby effectively suppressing overthinking. Extensive experiments validate that VeriThinker substantially reduces reasoning chain lengths while maintaining or even slightly improving accuracy. When applied to DeepSeek-R1-Distill-Qwen-7B, our approach reduces reasoning tokens on MATH500 from 3790 to 2125 while improving accuracy by 0.8% (94.0% to 94.8%), and on AIME25, tokens decrease from 14321 to 10287 with a 2.1% accuracy gain (38.7% to 40.8%). Additionally, our experiments demonstrate that VeriThinker can also be zero-shot generalized to speculative reasoning. Code is available at https://github.com/czg1225/VeriThinker
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。