KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection
Se-Hyun Choi, Tianqing Fang, Zhaowei Wang, Yangqiu Song · 2023
Large Language Models (LLMs) have demonstrated remarkable human-level natural language generation capabilities.However, their potential to generate misinformation, often called the hallucination problem, poses a significant risk to their deployment.A common approach to address this issue is to retrieve relevant knowledge and fine-tune the LLM with the knowledge in its input.Unfortunately, this method incurs high training costs and may cause catastrophic forgetting for multitasking models.To overcome these limitations, we propose a knowledge-constrained decoding method called KCTS (Knowledge-Constrained Tree Search), which guides a frozen LM to generate text aligned with the reference knowledge at each decoding step using a knowledge classifier score and MCTS (Monte-Carlo Tree Search).To adapt the sequence-level knowledge classifier to token-level guidance, we also propose a novel token-level hallucination detection method called RIPA (Reward Inflection Point Approximation).Our empirical results on knowledge-grounded dialogue and abstractive summarization demonstrate the strength of KCTS 1 as a plug-and-play, model-agnostic decoding method that can effectively reduce hallucinations in natural language generation.