Logo image
Back
TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination via Latent Truthful-Guided Pre-Intervention
Conference proceeding   Open access

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination via Latent Truthful-Guided Pre-Intervention

Jinhao Duan, Fei Kong, Hao Cheng, James Diffenderfer, Bhavya Kailkhura, Lichao Sun, Xiaofeng Zhu, Xiaoshuang Shi and Kaidi Xu
Proceedings / IEEE International Conference on Computer Vision, pp 7372-7382
19 Oct 2025
DOI: https://doi.org/10.1109/ICCV51701.2025.00692
url
https://arxiv.org/pdf/2503.10602View
Open

Abstract

Communication systems Computer networks HTTP large vision-language models object hallucination Protocols Radio access networks Regional area networks Space communications Video equipment Videos Wide Area Networks
Object Hallucination (\text{OH}) has been acknowledged as one of the major trustworthy challenges in Large VisionLanguage Models (LVLMs). Recent advancements in Large Language Models (LLMs) indicate that internal states, such as hidden states, encode the "overall truthfulness" of generated responses. However, it remains under-explored how internal states in LVLMs function and whether they could serve as "per-token" hallucination indicators, which is essential for mitigating O H . In this paper, we first conduct an in-depth exploration of LVLM internal states with OH issues and discover that LVLM internal states are high-specificity per-token indicators of hallucination behaviors. Moreover, different LVLMs encode universal patterns of hallucinations in common latent subspaces, indicating that there exist "generic truthful directions" shared by various LVLMs. Based on these discoveries, we propose Truthful-Guided Pre-Intervention (TruthPrInt) that first learns the truthful direction of LVLM decoding and then applies truthful-guided inferencetime intervention during LVLM decoding. We further propose ComnHallu to enhance both cross-LVLM and crossdata hallucination detection transferability by constructing and aligning hallucination latent subspaces. We evaluate TruthPrInt in extensive experimental settings, including in-domain and out-of-domain scenarios, over popular LVLMs and OH benchmarks. Experimental results indicate that TruthPrInt significantly outperforms state-of-the-art methods. Codes will be available at https://github.com/jinhaoduan/TruthPrInt.

Metrics

1 Record Views

Details

Logo image