通过推理轨迹形状预测大模型思维可靠性，无需黑箱访问。
Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought
- 用推理过程的熵变化曲线形状判断模型可信度
- 在多模型、多数据集上均保持稳定有效
- 适合用于高风险任务中的结果筛选与优先级排序
理解链式思维推理中的不确定性对大语言模型的可靠部署至关重要。本文提出一种基于轨迹形状而非数值大小的简单有效诊断方法。该信号在黑箱环境下易于获取，具有可解释性且成本低廉，同时在不同模型和数据集上表现出鲁棒性。通过大规模消融实验与跨领域复现，验证了其在选择性预测与任务优先级划分中的实用性。研究揭示了推理任务中不确定性动态的一般规律，尤其适用于数值型与离散答案场景。
原文摘要 · Abstract (English)
Understanding uncertainty in chain-of-thought reasoning is critical for reliable deployment of large language models. In this work, we propose a simple yet effective diagnostic approach based on trajectory shape rather than scalar magnitude. We show that this signal is practical, interpretable, and inexpensive to obtain in black-box settings, while remaining robust across models and datasets. Through extensive ablations and cross-domain replications, we demonstrate its utility for selective prediction and triage. Our findings offer a generalizable insight into uncertainty dynamics in reasoning tasks, with particular focus on numeric and discrete-answer settings.
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。