Dyve用快慢思维提升大模型推理错误检测能力
Dyve: Thinking Fast and Slow for Dynamic Process Verification
- 结合快思（系统1）与慢思（系统2）分层验证推理过程
- 在ProcessBench和MATH上超越现有验证器，提升Best-of-N效果
- 通过一致性过滤与蒙特卡洛估计生成高质量监督信号
我们提出Dyve，一种动态过程验证器，受卡尼曼双系统理论启发，通过自适应融合快速的逐标记确认（系统1）与深度分析（系统2）来增强大语言模型的推理错误检测能力。Dyve采用新颖的逐步共识过滤过程监督技术，结合蒙特卡洛估计与基于LLM的评估，从噪声数据中提炼高质量监督信号。在ProcessBench和MATH数据集上的实验结果表明，Dyve显著优于现有基于过程的验证器，并在Best-of-N设置下有效提升性能。
原文摘要 · Abstract (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.
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。