Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking

Large language models (LLMs) demonstrate exceptional capabilities, yet still face the hallucination issue.Typical text generation approaches adopt an auto-regressive generation without deliberate reasoning, often leading to untrustworthy and factually inaccurate responses.In this paper, we propose HaluSearch, a novel framework that incorporates tree search-based algorithms (e.g., MCTS) to enable an explicit slow thinking generation process for mitigating hallucinations during inference.Specifically, HaluSearch frames text generation as a step-by-step reasoning process, using a self-evaluation reward model to score each generation step and guide the tree search towards the most reliable generation pathway.To balance efficiency and quality, we introduce a hierarchical system switch mechanism inspired by the dual process theory in cognitive science , which dynamically switches between fast and slow thinking modes at both instance and step levels.We conduct extensive experiments on both English and Chinese datasets, and the results show that our approach significantly outperforms baseline approaches.