Dyve：为动态过程验证而设计的《快思慢想》

Dyve: Thinking Fast and Slow for Dynamic Process Verification

February 16, 2025

作者: Jianyuan Zhong, Zeju Li, Zhijian Xu, Xiangyu Wen, Qiang Xu

cs.AI

摘要

我们提出了Dyve，这是一种动态过程验证器，通过整合快速思考和慢速思考，受康奈曼的系统理论启发，增强了大型语言模型中的推理错误检测。Dyve自适应地应用立即的令牌级确认System 1来处理简单步骤，而对于复杂步骤则采用全面分析System 2。利用一种新颖的逐步共识过滤的过程监督技术，将蒙特卡洛估计与基于LLM的评估相结合，Dyve从嘈杂数据中筛选出高质量的监督信号。在ProcessBench和MATH数据集上的实验结果证实，Dyve明显优于现有基于过程的验证器，并提升了在Best-of-N设置中的性能。

English

We present Dyve, a dynamic process verifier that enhances reasoning error detection in large language models by integrating fast and slow thinking, inspired by Kahneman's Systems Theory. Dyve adaptively applies immediate token-level confirmation System 1 for straightforward steps and comprehensive analysis System 2 for complex ones. Leveraging a novel step-wise consensus-filtered process supervision technique, combining Monte Carlo estimation with LLM based evaluation, Dyve curates high-quality supervision signals from noisy data. Experimental results on ProcessBench and the MATH dataset confirm that Dyve significantly outperforms existing process-based verifiers and boosts performance in Best-of-N settings.