Dyve：動態程序驗證中的快思慢想

摘要

我們提出Dyve，這是一個動態過程驗證器，它通過整合快速與慢速思維來增強大型語言模型中的推理錯誤檢測，其靈感來自卡尼曼的系統理論。Dyve自適應地應用即時詞元級確認的系統1來處理簡單步驟，並運用全面分析的系統2來應對複雜情況。借助一種新穎的逐步共識過濾過程監督技術，該技術結合了蒙特卡羅估計與基於LLM的評估，Dyve從噪聲數據中提煉出高質量的監督信號。在ProcessBench和MATH數據集上的實驗結果證實，Dyve顯著優於現有的基於過程的驗證器，並在最佳N選設置中提升了性能。

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.

Dyve：動態程序驗證中的快思慢想

Dyve: Thinking Fast and Slow for Dynamic Process Verification

摘要

Support