@inproceedings{li-etal-2026-looking,
title = "Looking Closer When Unsure: {VIGOR}, A Training-Free Framework for Mitigating Object Hallucination in Multimodal Large Language Models",
author = "Li, Jiaxin and
Chen, Yixiang and
Lai, Lefan and
Zhao, Geng and
Long, Xiaohan and
Hu, Xuming",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.72/",
pages = "1463--1484",
ISBN = "979-8-89176-462-0",
abstract = "Object hallucination remains a major challenge in Multimodal Large Language Models (MLLMs), even though they have achieved strong performance across widely vision-language tasks. A key reason for object hallucination is limited fine-grained visual grounding provided by fixed-resolution visual encoding. In this paper, we propose Visual Inference Gating for Object Refinement (VIGOR), a training-free inference-time framework for binary object verification. VIGOR adopts a selective coarse-to-fine pipeline that improve visual grounding without the overhead of always-on multi-view inspection. It first uses the global yes{--}no margin to estimate whether the available evidence is sufficient. When the evidence is insufficient, VIGOR performs local refinement on uncertain cases using a small set of overlapping crops. Finally, VIGOR combines global and local evidence with an asymmetric decision rule. Experiments on three benchmark datasets across five MLLM backbones show that VIGOR consistently outperforms strong training-free baselines, recovering missed fine-grained evidence while maintaining robust performance on challenging visual reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-looking">
<titleInfo>
<title>Looking Closer When Unsure: VIGOR, A Training-Free Framework for Mitigating Object Hallucination in Multimodal Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixiang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lefan</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geng</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaohan</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuming</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Object hallucination remains a major challenge in Multimodal Large Language Models (MLLMs), even though they have achieved strong performance across widely vision-language tasks. A key reason for object hallucination is limited fine-grained visual grounding provided by fixed-resolution visual encoding. In this paper, we propose Visual Inference Gating for Object Refinement (VIGOR), a training-free inference-time framework for binary object verification. VIGOR adopts a selective coarse-to-fine pipeline that improve visual grounding without the overhead of always-on multi-view inspection. It first uses the global yes–no margin to estimate whether the available evidence is sufficient. When the evidence is insufficient, VIGOR performs local refinement on uncertain cases using a small set of overlapping crops. Finally, VIGOR combines global and local evidence with an asymmetric decision rule. Experiments on three benchmark datasets across five MLLM backbones show that VIGOR consistently outperforms strong training-free baselines, recovering missed fine-grained evidence while maintaining robust performance on challenging visual reasoning.</abstract>
<identifier type="citekey">li-etal-2026-looking</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.72/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1463</start>
<end>1484</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Looking Closer When Unsure: VIGOR, A Training-Free Framework for Mitigating Object Hallucination in Multimodal Large Language Models
%A Li, Jiaxin
%A Chen, Yixiang
%A Lai, Lefan
%A Zhao, Geng
%A Long, Xiaohan
%A Hu, Xuming
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F li-etal-2026-looking
%X Object hallucination remains a major challenge in Multimodal Large Language Models (MLLMs), even though they have achieved strong performance across widely vision-language tasks. A key reason for object hallucination is limited fine-grained visual grounding provided by fixed-resolution visual encoding. In this paper, we propose Visual Inference Gating for Object Refinement (VIGOR), a training-free inference-time framework for binary object verification. VIGOR adopts a selective coarse-to-fine pipeline that improve visual grounding without the overhead of always-on multi-view inspection. It first uses the global yes–no margin to estimate whether the available evidence is sufficient. When the evidence is insufficient, VIGOR performs local refinement on uncertain cases using a small set of overlapping crops. Finally, VIGOR combines global and local evidence with an asymmetric decision rule. Experiments on three benchmark datasets across five MLLM backbones show that VIGOR consistently outperforms strong training-free baselines, recovering missed fine-grained evidence while maintaining robust performance on challenging visual reasoning.
%U https://aclanthology.org/2026.findings-emnlp.72/
%P 1463-1484
Markdown (Informal)
[Looking Closer When Unsure: VIGOR, A Training-Free Framework for Mitigating Object Hallucination in Multimodal Large Language Models](https://aclanthology.org/2026.findings-emnlp.72/) (Li et al., Findings 2026)
ACL