Dyve: Thinking Fast and Slow for Dynamic Process Verification

ACL ARR 2025 February Submission628 Authors

Abstract: 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.

Paper Type: Short

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: Large Language Models (LLMs), Multi-Step Reasoning, Process Verification, Process Reward Modeling, Dual-System Theory (System 1 & System 2), Adaptive Computation Budgeting, Monte Carlo Estimation, Consensus Filtering, Process Supervision

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data resources

Languages Studied: English, Chinese

Submission Number: 628