Statistical Early Stopping for Reasoning Models
University of Pennsylvania, University of Pennsylvania · The Wharton School, University of Pennsylvania · New Jersey Institute of Technology · University of Pennsylvania · Washington University, Saint Louis · Argonne National Laboratory
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given ill-posed or ambiguous queries. We introduce statistically principled early stopping methods that monitor uncertainty signals during generation to mitigate this issue. Our first approach is nonparametric and provides finite-sample guarantees on the probability of halting too early on well-posed queries. Our second approach is parametric: it models inter-arrival times of uncertainty keywords as a renewal process and applies sequential testing for stopping. We conduct empirical evaluations on reasoning tasks across several domains and models. Our results indicate that uncertainty-aware early stopping can improve both efficiency and reliability in LLM reasoning. The performance varies across domains, and we observe especially significant gains for math reasoning.