Salvato in:
Dettagli Bibliografici
Autori principali: Song, Junru, Hu, Yimeng, Chen, Yijing, Li, Huining, Li, Qian, Cui, Lizhen, Du, Yuntao
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.26419
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914516277657600
author Song, Junru
Hu, Yimeng
Chen, Yijing
Li, Huining
Li, Qian
Cui, Lizhen
Du, Yuntao
author_facet Song, Junru
Hu, Yimeng
Chen, Yijing
Li, Huining
Li, Qian
Cui, Lizhen
Du, Yuntao
contents Large Vision-Language Models (VLMs) have achieved remarkable multimodal performance yet remain prone to factual hallucinations, particularly in long-tail or specialized domains. Moreover, current models exhibit a weak capacity to refuse queries that exceed their parametric knowledge. In this paper, we propose a systematic framework to enhance the refusal capability of VLMs when facing such unknown questions. We first curate a model-specific "Visual-Idk" (Visual-I don't know) dataset, leveraging multi-sample consistency probing to distinguish between known and unknown facts. We then align the model using supervised fine-tuning followed by preference-aware optimization (e.g., DPO, ORPO) to effectively delineate its knowledge boundaries. Results on the Visual-Idk dataset show our method improves the Truthful Rate from 57.9\% to 67.3\%. Additionally, internal probing also demonstrates that the model genuinely recognizes its boundaries instead of just memorizing refusal patterns. Our framework further generalizes to out-of-distribution medical and perceptual domains, providing a robust path toward more trustworthy and prudent visual assistants.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26419
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Delineating Knowledge Boundaries for Honest Large Vision-Language Models
Song, Junru
Hu, Yimeng
Chen, Yijing
Li, Huining
Li, Qian
Cui, Lizhen
Du, Yuntao
Computer Vision and Pattern Recognition
Artificial Intelligence
Large Vision-Language Models (VLMs) have achieved remarkable multimodal performance yet remain prone to factual hallucinations, particularly in long-tail or specialized domains. Moreover, current models exhibit a weak capacity to refuse queries that exceed their parametric knowledge. In this paper, we propose a systematic framework to enhance the refusal capability of VLMs when facing such unknown questions. We first curate a model-specific "Visual-Idk" (Visual-I don't know) dataset, leveraging multi-sample consistency probing to distinguish between known and unknown facts. We then align the model using supervised fine-tuning followed by preference-aware optimization (e.g., DPO, ORPO) to effectively delineate its knowledge boundaries. Results on the Visual-Idk dataset show our method improves the Truthful Rate from 57.9\% to 67.3\%. Additionally, internal probing also demonstrates that the model genuinely recognizes its boundaries instead of just memorizing refusal patterns. Our framework further generalizes to out-of-distribution medical and perceptual domains, providing a robust path toward more trustworthy and prudent visual assistants.
title Delineating Knowledge Boundaries for Honest Large Vision-Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.26419