Bold Claims or Self-Doubt? Factuality Hallucination Type Detection via Belief State

Dongyu Zhang, Qingqing Hong, Bingxuan Hou, Jiayi Lin, Chenyang Zhang, Jialin Li, Junli Wang


Abstract
Large language models are prone to generating hallucination that deviates from factual information. Existing studies mainly focus on detecting the presence of hallucinations but lack a systematic classification approach, which hinders deeper exploration of their characteristics. To address this, we introduce the concept of belief state, which quantifies the model’s confidence in its own responses. We define the belief state of the model based on self-consistency, leveraging answer repetition rates to label confident and uncertain states. Based on this, we categorize factuality hallucination into two types: Overconfident Hallucination and Unaware Hallucination. Furthermore, we propose BAFH, a factuality hallucination type detection method. By training a classifier on model’s hidden states, we establish a link between hidden states and belief states, enabling efficient and automatic hallucination type detection. Experimental results demonstrate the effectiveness of BAFH and the differences between hallucination types.
Anthology ID:
2025.findings-emnlp.527
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9946–9959
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.527/
DOI:
Bibkey:
Cite (ACL):
Dongyu Zhang, Qingqing Hong, Bingxuan Hou, Jiayi Lin, Chenyang Zhang, Jialin Li, and Junli Wang. 2025. Bold Claims or Self-Doubt? Factuality Hallucination Type Detection via Belief State. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 9946–9959, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Bold Claims or Self-Doubt? Factuality Hallucination Type Detection via Belief State (Zhang et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.527.pdf
Checklist:
 2025.findings-emnlp.527.checklist.pdf