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.- Anthology ID:
- 2023.emnlp-main.867
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14035–14053
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.867
- DOI:
- 10.18653/v1/2023.emnlp-main.867
- Cite (ACL):
- Sehyun Choi, Tianqing Fang, Zhaowei Wang, and Yangqiu Song. 2023. KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14035–14053, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection (Choi et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.emnlp-main.867.pdf