Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models

Unfortunately, the post-processing methods widely used in existing studies are suboptimal for In recent years, Large Language Models (LLMs) the applications of hallucination detection models have demonstrated remarkable performance in a variety for LLMs in practice. First, existing postprocessing of natural language processing (NLP) applications methods often suffer from extreme computation (Brown et al., 2020; Chowdhery et al., 2022; costs and high latency. In order to identify Touvron et al., 2023a; Scao et al., 2022; Zhang hallucinations in input text without ground et al., 2022). However, the widespread adoption of truth references (otherwise the task would downgrade LLMs has highlighted a critical problem, i.e., hallucination. to a simple fact verification task), hallucination Hallucination refers to the cases where detection models need to be powerful and LLMs generate responses that are logically coherent knowledgeable on their own. SOTA detection methods but factually incorrect or misleading (Maynez are often implemented with LLMs (e.g., chat-et al., 2020; Zhou et al., 2020; Liu et al., 2021; GPT, LLaMA, OPT) directly (Manakul et al., 2023;