Work

LAFaCT: Attribution-based Localization and Focused Sequential Analysis of Fact-Critical Tokens for Hallucination Detection

Year: 2026

Type: conference-paper

Abstract: Large Language Models (LLMs) suffer from hallucinations, severely undermining their reliability.While white-box hallucination detection methods that leverage hidden states prevail, they fail to identify and focus on factcritical information when analyzing token sequences.To address this, we propose LAFaCT, a Localize-then-Analyze detection framework.It first localizes fact-critical tokens using Factual Criticality, a novel metric derived from feature attribution.A subsequent stage then performs a focused sequential analysis on their hidden states.Extensive experiments on eight benchmarks and multiple model families confirm LAFaCT as the new state-of-the-art, with in-depth analyses validating the effectiveness of its core token-localization strategy.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2026.acl-long.312

Authors: Xin Wang, Jiahao Li, Licheng Zhang, Zhendong Mao

Institution: University of Science and Technology of China

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Ministry of Education of the People's Republic of China, National Science and Technology Major Project

Awards: G4729153174, G7336938272