用熵累积值控制思考长度，让大模型少想多做。
Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
- 用熵累积平均值衡量思考探索程度，动态判断何时停止。
- 简单题回答长度减少71%，解题能力不下降。
- 适合追求高效推理的场景，如实时问答系统。
大型语言模型在复杂问题上使用长链式思维（CoT）展现出强大推理能力，但常出现过度思考现象，即对简单问题生成冗长推理步骤，降低效率且难以适配问题复杂度。为此，本文提出一种新度量指标——分词熵累积平均值（TECA），用于衡量推理过程中的探索程度。进一步提出“简短探索后决策”新范式，结合累积熵调节（CER）机制，利用TECA帮助模型动态确定最优结论时机，实现高效推理。在多个数学基准测试中，该方法显著缓解过度思考问题，平均响应长度在简单数据集上减少高达71%，同时保持解题能力，验证了其在提升推理效率与适应性方面的有效性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated remarkable reasoning abilities on complex problems using long Chain-of-Thought (CoT) reasoning. However, they often suffer from overthinking, meaning generating unnecessarily lengthy reasoning steps for simpler problems. This issue may degrade the efficiency of the models and make them difficult to adapt the reasoning depth to the complexity of problems. To address this, we introduce a novel metric Token Entropy Cumulative Average (TECA), which measures the extent of exploration throughout the reasoning process. We further propose a novel reasoning paradigm named "Explore Briefly, Then Decide", with an associated Cumulative Entropy Regulation (CER) mechanism. This paradigm leverages TECA to help the model dynamically determine the optimal point to conclude its thought process and provide a final answer, thus achieving efficient reasoning. Experimental results across diverse mathematical benchmarks show that our approach substantially mitigates overthinking without sacrificing problem solving ability. With our thinking paradigm, the average response length decreases by up to 71% on simpler datasets, demonstrating the effectiveness of our method in creating a more efficient and adaptive reasoning process.
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。