Chain Of Natural Language Inference For Reducing Large Language Model Ungrounded Hallucinations

Lei Deren, Li Yaxi, Hu Mengya, Wang Mingyu, Yun Vincent, Ching Emily, Kamal Eslam. Arxiv 2023

[Paper]    
Applications Fine Tuning Pretraining Methods Prompting Reinforcement Learning Tools Training Techniques

Large language models (LLMs) can generate fluent natural language texts when given relevant documents as background context. This ability has attracted considerable interest in developing industry applications of LLMs. However, LLMs are prone to generate hallucinations that are not supported by the provided sources. In this paper, we propose a hierarchical framework to detect and mitigate such ungrounded hallucination. Our framework uses Chain of Natural Language Inference (CoNLI) for hallucination detection and hallucination reduction via post-editing. Our approach achieves state-of-the-art performance on hallucination detection and enhances text quality through rewrite, using LLMs without any fine-tuning or domain-specific prompt engineering. We show that this simple plug-and-play framework can serve as an effective choice for hallucination detection and reduction, achieving competitive performance across various contexts.

Similar Work