arXiv 2510.028162025-10-03cs.AIcs.CL

NCV：一种面向大语言模型推理中低成本结构化错误定位的节点级一致性验证方法

NCV: A Node-Wise Consistency Verification Approach for Low-Cost Structured Error Localization in LLM Reasoning

Beijing University of Posts and Telecommunications（北京邮电大学）；Shanghai Jiao Tong University（上海交通大学）；Ant Group（蚂蚁集团）；Tsinghua University（清华大学）；Inner Mongolia Research Institute of SJTU（内蒙古大学SJTU研究所）

Yulong Zhang, Li Wang, Wei Du, Peilin Li, Yuqin Dai Zhiyuan Zhao, Lingyong Fang, Ziniu Liu, Ru Zhang, Huijia Zhu, Gongshen Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对大语言模型多步推理验证错误定位不准、成本高的问题，提出无需训练的节点级一致性验证框架NCV，将验证转化为节点二值检查，在公开数据集上F1提升10%-25%，token用量降低6-58倍。

摘要：

大语言模型的多步推理验证因错误定位不精准和token成本高昂而颇具难度。现有方法要么评估完整推理链，存在注意力稀释问题，要么依赖成本高昂的多次采样。我们提出节点级一致性验证（Node-wise Consistency Verification，NCV），这是一个无需训练的框架，将验证转化为节点层面的轻量二值一致性检查。通过将思维链分解为相互关联的验证节点，NCV能精准定位错误，且避免不必要的长文本生成。实验表明，该方法提升了可解释性与效率，为可靠的LLM推理验证提供了可扩展的解决方案。在公开数据集上，NCV的F1分数较基线提升10%至25%，同时token使用量比基于CoT的验证器等传统方法少6倍至58倍。

英文摘要：

Verifying multi-step reasoning in large language models is difficult due to imprecise error localization and high token costs. Existing methods either assess entire reasoning chains, suffering attention dilution, or rely on expensive multi-sampling. We introduce Node-wise Consistency Verification (NCV), a training-free framework that recasts verification as lightweight binary consistency checks at the node level. By decomposing the chain of thought into interconnected verification nodes, NCV precisely localizes errors and avoids unnecessary long-form generation. Experiments demonstrate that our approach enhances interpretability and efficiency, presenting a scalable solution for reliable LLM reasoning verification. On public datasets, NCV achieves a 10\% to 25\% improvement in F1 scores over baselines while utilizing $6\times$~$58\times$ fewer tokens than traditional methods like CoT-based verifiers.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。