Think When You Need: 自适应思维链学习
Think When You Need: Self-Adaptive Chain-of-Thought Learning
AI总结：
针对思维链推理在简单问题上过度思考的低效问题，提出通过长度与质量比较构建奖励的自适应学习方法，可在保持准确率的同时生成更简洁的推理，还适用于无真实标签的模糊任务。
摘要：
思维链（Chain of Thought, CoT）推理可提升语言模型性能，但常导致在简单问题上出现低效的“过度思考”。我们发现现有直接惩罚推理长度的方法未能考虑问题复杂度的差异。我们的方法通过长度与质量比较构建奖励，其背后的理论假设可同时提升解的正确性与简洁性。此外，我们进一步将该方法应用于无真实标签的模糊任务。在多个推理基准上的实验表明，该方法在保持准确率的同时，生成的解释显著更简洁，有效教会模型“按需思考”。
英文摘要：
Chain of Thought (CoT) reasoning enhances language models' performance but often leads to inefficient "overthinking" on simple problems. We identify that existing approaches directly penalizing reasoning length fail to account for varying problem complexity. Our approach constructs rewards through length and quality comparisons, guided by theoretical assumptions that jointly enhance solution correctness with conciseness. Moreover, we further demonstrate our method to fuzzy tasks where ground truth is unavailable. Experiments across multiple reasoning benchmarks demonstrate that our method maintains accuracy while generating significantly more concise explanations, effectively teaching models to "think when needed."
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
