Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Kedi, Chen, Qin, Zhou, Jie, Tao, Xinqi, Ding, Bowen, Xie, Jingwen, Xie, Mingchen, Li, Peilong, Zheng, Feng, He, Liang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908302311424000
author Chen, Kedi
Chen, Qin
Zhou, Jie
Tao, Xinqi
Ding, Bowen
Xie, Jingwen
Xie, Mingchen
Li, Peilong
Zheng, Feng
He, Liang
author_facet Chen, Kedi
Chen, Qin
Zhou, Jie
Tao, Xinqi
Ding, Bowen
Xie, Jingwen
Xie, Mingchen
Li, Peilong
Zheng, Feng
He, Liang
contents Large Language Models (LLMs) are prone to hallucination with non-factual or unfaithful statements, which undermines the applications in real-world scenarios. Recent researches focus on uncertainty-based hallucination detection, which utilizes the output probability of LLMs for uncertainty calculation and does not rely on external knowledge or frequent sampling from LLMs. Whereas, most approaches merely consider the uncertainty of each independent token, while the intricate semantic relations among tokens and sentences are not well studied, which limits the detection of hallucination that spans over multiple tokens and sentences in the passage. In this paper, we propose a method to enhance uncertainty modeling with semantic graph for hallucination detection. Specifically, we first construct a semantic graph that well captures the relations among entity tokens and sentences. Then, we incorporate the relations between two entities for uncertainty propagation to enhance sentence-level hallucination detection. Given that hallucination occurs due to the conflict between sentences, we further present a graph-based uncertainty calibration method that integrates the contradiction probability of the sentence with its neighbors in the semantic graph for uncertainty calculation. Extensive experiments on two datasets show the great advantages of our proposed approach. In particular, we obtain substantial improvements with 19.78% in passage-level hallucination detection.
format Preprint
id arxiv_https___arxiv_org_abs_2501_02020
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection
Chen, Kedi
Chen, Qin
Zhou, Jie
Tao, Xinqi
Ding, Bowen
Xie, Jingwen
Xie, Mingchen
Li, Peilong
Zheng, Feng
He, Liang
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) are prone to hallucination with non-factual or unfaithful statements, which undermines the applications in real-world scenarios. Recent researches focus on uncertainty-based hallucination detection, which utilizes the output probability of LLMs for uncertainty calculation and does not rely on external knowledge or frequent sampling from LLMs. Whereas, most approaches merely consider the uncertainty of each independent token, while the intricate semantic relations among tokens and sentences are not well studied, which limits the detection of hallucination that spans over multiple tokens and sentences in the passage. In this paper, we propose a method to enhance uncertainty modeling with semantic graph for hallucination detection. Specifically, we first construct a semantic graph that well captures the relations among entity tokens and sentences. Then, we incorporate the relations between two entities for uncertainty propagation to enhance sentence-level hallucination detection. Given that hallucination occurs due to the conflict between sentences, we further present a graph-based uncertainty calibration method that integrates the contradiction probability of the sentence with its neighbors in the semantic graph for uncertainty calculation. Extensive experiments on two datasets show the great advantages of our proposed approach. In particular, we obtain substantial improvements with 19.78% in passage-level hallucination detection.
title Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2501.02020