提出方法解决推理模型过度思考问题，提升效率与准确性。
THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
- 通过分析题目难度与最优生成长度的关系，发现模型普遍不匹配。
- 在简单题上错误率高达40%，复杂题表现更差。
- 提出无需训练的解码技巧，显著改善模型校准能力。
推理模型在复杂任务上表现优异，但普遍存在过度思考问题——生成大量无助于提升准确率的冗余文本。本文引入近似的问题难度度量，揭示了问题难度与最优生成长度之间存在明确关系，并评估多种推理模型在分配最优生成长度方面的校准程度。结果表明，多数模型校准较差，尤其在简单题目上更为明显。为评估其在简单问题上的表现，我们构建了DUMB500数据集，包含极简数学、推理、代码及任务题，并在同一领域对模型同时测试其在简单题与前沿基准中的极端难题表现。最后，我们提出THOUGHTTERMINATOR，一种无需训练的黑盒解码策略，可显著提升推理模型的校准能力。
原文摘要 · Abstract (English)
Reasoning models have demonstrated impressive performance on difficult tasks that traditional language models struggle at. However, many are plagued with the problem of overthinking--generating large amounts of unnecessary tokens which don't improve accuracy on a question. We introduce approximate measures of problem-level difficulty and demonstrate that a clear relationship between problem difficulty and optimal token spend exists, and evaluate how well calibrated a variety of reasoning models are in terms of efficiently allocating the optimal token count. We find that in general, reasoning models are poorly calibrated, particularly on easy problems. To evaluate calibration on easy questions we introduce DUMB500, a dataset of extremely easy math, reasoning, code, and task problems, and jointly evaluate reasoning model on these simple examples and extremely difficult examples from existing frontier benchmarks on the same task domain. Finally, we introduce THOUGHTTERMINATOR, a training-free black box decoding technique that significantly improves reasoning model calibration.
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。