发现大模型推理失败前的早期信号，提前终止无效推理。
Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
- 通过分析推理过程和最后输入词的隐藏状态，识别失败预兆。
- 测试时监控可减少62.7%-93.6%的计算耗时，效率大幅提升。
- 适合追求高效可靠推理的部署场景，尤其适用于资源受限环境。
当前大型推理模型的问答范式常忽视某些问题已超出模型能力边界，导致冗长但无产出的推理。本文研究大型推理模型是否在早期表现出可预测失败的信号，并探讨能否利用这些信号来缓解无效推理。在黑盒设置下，我们发现推理表达式中包含失败预测信号；在白盒设置下，证明最后一个输入词的隐藏状态蕴含了在评估设定下无法正确解答问题的预测信息。基于此，我们提出两种测试时监控策略：推理表达式监控与隐藏状态监控，可在几乎不损失准确率的前提下，将令牌消耗降低62.7%-93.6%，显著提升效率与可靠性。
原文摘要 · Abstract (English)
Current answering paradigms for Large Reasoning Models (LRMs) often fail to account for the fact that some questions may lie beyond the model's operational capability boundary, leading to long but unproductive reasoning. In this paper, we study whether LRMs expose early signals predictive of such cases, and whether these signals can be used to mitigate unproductive reasoning. In black-box settings, we find that reasoning expressions contain failure-predictive signals. In white-box settings, we show that the hidden states of the last input token contain information that is predictive of whether a question will not be solved correctly under our evaluation setup. Building on these observations, we propose two test-time monitoring strategies: reasoning expression monitoring and hidden states monitoring, that reduce token usage by 62.7-93.6%, substantially improving efficiency and reliability while largely preserving accuracy.
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。