Prompt-Guided Internal States for Hallucination Detection of Large Language Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Fujie, Yu, Peiqi, Yi, Biao, Zhang, Baolei, Li, Tong, Liu, Zheli
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908373747761152
author Zhang, Fujie
Yu, Peiqi
Yi, Biao
Zhang, Baolei
Li, Tong
Liu, Zheli
author_facet Zhang, Fujie
Yu, Peiqi
Yi, Biao
Zhang, Baolei
Li, Tong
Liu, Zheli
contents Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of tasks in different domains. However, they sometimes generate responses that are logically coherent but factually incorrect or misleading, which is known as LLM hallucinations. Data-driven supervised methods train hallucination detectors by leveraging the internal states of LLMs, but detectors trained on specific domains often struggle to generalize well to other domains. In this paper, we aim to enhance the cross-domain performance of supervised detectors with only in-domain data. We propose a novel framework, prompt-guided internal states for hallucination detection of LLMs, namely PRISM. By utilizing appropriate prompts to guide changes to the structure related to text truthfulness in LLMs' internal states, we make this structure more salient and consistent across texts from different domains. We integrated our framework with existing hallucination detection methods and conducted experiments on datasets from different domains. The experimental results indicate that our framework significantly enhances the cross-domain generalization of existing hallucination detection methods.
format Preprint
id arxiv_https___arxiv_org_abs_2411_04847
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prompt-Guided Internal States for Hallucination Detection of Large Language Models
Zhang, Fujie
Yu, Peiqi
Yi, Biao
Zhang, Baolei
Li, Tong
Liu, Zheli
Computation and Language
Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of tasks in different domains. However, they sometimes generate responses that are logically coherent but factually incorrect or misleading, which is known as LLM hallucinations. Data-driven supervised methods train hallucination detectors by leveraging the internal states of LLMs, but detectors trained on specific domains often struggle to generalize well to other domains. In this paper, we aim to enhance the cross-domain performance of supervised detectors with only in-domain data. We propose a novel framework, prompt-guided internal states for hallucination detection of LLMs, namely PRISM. By utilizing appropriate prompts to guide changes to the structure related to text truthfulness in LLMs' internal states, we make this structure more salient and consistent across texts from different domains. We integrated our framework with existing hallucination detection methods and conducted experiments on datasets from different domains. The experimental results indicate that our framework significantly enhances the cross-domain generalization of existing hallucination detection methods.
title Prompt-Guided Internal States for Hallucination Detection of Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2411.04847