@inproceedings{li-etal-2025-visual,
title = "Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models",
author = "Li, Wei and
Huang, Zhen and
Li, Houqiang and
Lu, Le and
Lu, Yang and
Tian, Xinmei and
Shen, Xu and
Ye, Jieping",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.205/",
doi = "10.18653/v1/2025.acl-long.205",
pages = "4048--4080",
ISBN = "979-8-89176-251-0",
abstract = "Large Vision-Language Models (LVLMs) have shown impressive progress by integrating visual perception with linguistic understanding to produce contextually grounded outputs. Despite these advancements achieved, LVLMs still suffer from the hallucination problem, e.g., they tend to produce content that does not exist in the input images. Our investigation suggests that such hallucinations often stem from the deficiencies in fine-grained comprehension on the visual aspect, particularly when visual scenes exhibit appearance or semantic similarities (e.g., bicycle vs. motorcycles, baseball bat vs. baseball). In this work, we show such hallucination is naturally mitigated via a novel method called visual evidence prompting, utilizing small visual models to complement the LVLMs. While traditional visual models are not adept at interacting with humans, they excel at perceiving the fine-grained image contents. By symbolizing the professional outputs of domain-expert models as prompts, the LVLM generalists are able to refer to these evidences as visual knowledge to generate more precise answers. Detailed analysis shows that visual evidence enables models to adjust and rectify the attribution and attention on the images, reducing visual confusion by suppressing false activation while enhancing correct ones. Extensive experiments and in-depth analysis demonstrate the effectiveness of our method. We hope our straightforward but insightful work enhances the comprehension of hallucination in LVLMs and offers valuable perspectives on addressing such challenges."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-visual">
<titleInfo>
<title>Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houqiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinmei</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieping</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Large Vision-Language Models (LVLMs) have shown impressive progress by integrating visual perception with linguistic understanding to produce contextually grounded outputs. Despite these advancements achieved, LVLMs still suffer from the hallucination problem, e.g., they tend to produce content that does not exist in the input images. Our investigation suggests that such hallucinations often stem from the deficiencies in fine-grained comprehension on the visual aspect, particularly when visual scenes exhibit appearance or semantic similarities (e.g., bicycle vs. motorcycles, baseball bat vs. baseball). In this work, we show such hallucination is naturally mitigated via a novel method called visual evidence prompting, utilizing small visual models to complement the LVLMs. While traditional visual models are not adept at interacting with humans, they excel at perceiving the fine-grained image contents. By symbolizing the professional outputs of domain-expert models as prompts, the LVLM generalists are able to refer to these evidences as visual knowledge to generate more precise answers. Detailed analysis shows that visual evidence enables models to adjust and rectify the attribution and attention on the images, reducing visual confusion by suppressing false activation while enhancing correct ones. Extensive experiments and in-depth analysis demonstrate the effectiveness of our method. We hope our straightforward but insightful work enhances the comprehension of hallucination in LVLMs and offers valuable perspectives on addressing such challenges.</abstract>
<identifier type="citekey">li-etal-2025-visual</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.205</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.205/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>4048</start>
<end>4080</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models
%A Li, Wei
%A Huang, Zhen
%A Li, Houqiang
%A Lu, Le
%A Lu, Yang
%A Tian, Xinmei
%A Shen, Xu
%A Ye, Jieping
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F li-etal-2025-visual
%X Large Vision-Language Models (LVLMs) have shown impressive progress by integrating visual perception with linguistic understanding to produce contextually grounded outputs. Despite these advancements achieved, LVLMs still suffer from the hallucination problem, e.g., they tend to produce content that does not exist in the input images. Our investigation suggests that such hallucinations often stem from the deficiencies in fine-grained comprehension on the visual aspect, particularly when visual scenes exhibit appearance or semantic similarities (e.g., bicycle vs. motorcycles, baseball bat vs. baseball). In this work, we show such hallucination is naturally mitigated via a novel method called visual evidence prompting, utilizing small visual models to complement the LVLMs. While traditional visual models are not adept at interacting with humans, they excel at perceiving the fine-grained image contents. By symbolizing the professional outputs of domain-expert models as prompts, the LVLM generalists are able to refer to these evidences as visual knowledge to generate more precise answers. Detailed analysis shows that visual evidence enables models to adjust and rectify the attribution and attention on the images, reducing visual confusion by suppressing false activation while enhancing correct ones. Extensive experiments and in-depth analysis demonstrate the effectiveness of our method. We hope our straightforward but insightful work enhances the comprehension of hallucination in LVLMs and offers valuable perspectives on addressing such challenges.
%R 10.18653/v1/2025.acl-long.205
%U https://aclanthology.org/2025.acl-long.205/
%U https://doi.org/10.18653/v1/2025.acl-long.205
%P 4048-4080
Markdown (Informal)
[Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models](https://aclanthology.org/2025.acl-long.205/) (Li et al., ACL 2025)
ACL
- Wei Li, Zhen Huang, Houqiang Li, Le Lu, Yang Lu, Xinmei Tian, Xu Shen, and Jieping Ye. 2025. Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4048–4080, Vienna, Austria. Association for Computational Linguistics.