KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection

Sehyun Choi, Tianqing Fang, Zhaowei Wang, Yangqiu Song

Submission Type: Regular Long Paper

Submission Track: Natural Language Generation

Submission Track 2: Language Modeling and Analysis of Language Models

Keywords: Hallucination, Knowledge Grounding, Natural Language Generation, Constrained Decoding, Controllable Text Generation

TL;DR: A constrained decoding method using MCTS for faithful natural language generation grounded on reference knowledge.

Abstract: 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 multi-tasking 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 as a plug-and-play, model-agnostic decoding method that can effectively reduce hallucinations in natural language generation.

Submission Number: 3037