通过共享决策点验证大模型推理路径正确性
Correct Reasoning Paths Visit Shared Decision Pivots
- 发现正确推理路径都会经过一组共享决策点
- 在LogiQA、MedQA等数据集上提升推理准确率
- 无需真实标注即可自动生成训练数据
链式思维（CoT）揭示了大语言模型的中间推理过程，但大规模验证仍无解。本文提出决策点概念——任何正确推理路径都必须经过的最小可验证检查点。假设正确推理虽形式多样，但会收敛到相同决策点集合，而错误推理至少违反一个点。基于此，提出自训练流程：(i) 采样多样化推理路径并挖掘共享决策点，(ii) 用辅助验证器将每条路径压缩为聚焦决策点的短路径，(iii) 使用自生成输出对模型进行后训练。该方法无需真实推理数据或外部指标即可对齐推理。在LogiQA、MedQA和MATH500等标准基准上验证了有效性。
原文摘要 · Abstract (English)
Chain-of-thought (CoT) reasoning exposes the intermediate thinking process of large language models (LLMs), yet verifying those traces at scale remains unsolved. In response, we introduce the idea of decision pivots-minimal, verifiable checkpoints that any correct reasoning path must visit. We hypothesize that correct reasoning, though stylistically diverse, converge on the same pivot set, while incorrect ones violate at least one pivot. Leveraging this property, we propose a self-training pipeline that (i) samples diverse reasoning paths and mines shared decision pivots, (ii) compresses each trace into pivot-focused short-path reasoning using an auxiliary verifier, and (iii) post-trains the model using its self-generated outputs. The proposed method aligns reasoning without ground truth reasoning data or external metrics. Experiments on standard benchmarks such as LogiQA, MedQA, and MATH500 show the effectiveness of our method.
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。