@inproceedings{yin-etal-2026-plane,
title = "{PLANE}: Plug-and-Play Fine-Grained Visual Experts for Hallucination Mitigation in Large Vision-Language Models",
author = "Yin, Jianghao and
Yu, Lang and
Yu, Qianxi and
Chen, Qin and
Zhou, Jie and
Lei, Zhikai and
He, Liang",
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.1756/",
pages = "37559--37576",
ISBN = "979-8-89176-462-0",
abstract = "Large Vision-Language Models (LVLMs) commonly suffer from hallucinations, which appear as fabricating non-existent objects or outputting incorrect attributes and spatial relationships in images. Previous works empirically indicate that CLIP-style vision encoders tend to focus on primary objects while ignoring image details, which is one of the causes of hallucinations. To address this issue, we propose plug-and-play fine-grained visual experts (PLANE) comprising two components: LoRA visual experts operating on CLIP for multi-aspect image encoding, and an instruction-aware gate network for adaptive image feature fusion. During training, we construct a fine-grained image-caption pairs dataset, where images are described from three aspects: objects, attributes, and relations between objects. Image-caption pairs from different aspects are used to train the three fine-grained LoRA experts respectively. Aiming at comprehensively evaluate our method{'}s capabilities, we manually annotate a fine-grained hallucination evaluation benchmark for LVLMs which is GPT4-independent during evaluation phase (GIFT). We conduct experiments both on popular hallucination evaluation benchmarks and GIFT. The results show that our method effectively reduces hallucinations across models of different types and sizes while introducing minimal inference latency. Compared to advanced baselines, our model also demonstrates superior performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-etal-2026-plane">
<titleInfo>
<title>PLANE: Plug-and-Play Fine-Grained Visual Experts for Hallucination Mitigation in Large Vision-Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianghao</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianxi</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhikai</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">He</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>Large Vision-Language Models (LVLMs) commonly suffer from hallucinations, which appear as fabricating non-existent objects or outputting incorrect attributes and spatial relationships in images. Previous works empirically indicate that CLIP-style vision encoders tend to focus on primary objects while ignoring image details, which is one of the causes of hallucinations. To address this issue, we propose plug-and-play fine-grained visual experts (PLANE) comprising two components: LoRA visual experts operating on CLIP for multi-aspect image encoding, and an instruction-aware gate network for adaptive image feature fusion. During training, we construct a fine-grained image-caption pairs dataset, where images are described from three aspects: objects, attributes, and relations between objects. Image-caption pairs from different aspects are used to train the three fine-grained LoRA experts respectively. Aiming at comprehensively evaluate our method’s capabilities, we manually annotate a fine-grained hallucination evaluation benchmark for LVLMs which is GPT4-independent during evaluation phase (GIFT). We conduct experiments both on popular hallucination evaluation benchmarks and GIFT. The results show that our method effectively reduces hallucinations across models of different types and sizes while introducing minimal inference latency. Compared to advanced baselines, our model also demonstrates superior performance.</abstract>
<identifier type="citekey">yin-etal-2026-plane</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1756/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>37559</start>
<end>37576</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PLANE: Plug-and-Play Fine-Grained Visual Experts for Hallucination Mitigation in Large Vision-Language Models
%A Yin, Jianghao
%A Yu, Lang
%A Yu, Qianxi
%A Chen, Qin
%A Zhou, Jie
%A Lei, Zhikai
%A He, Liang
%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 yin-etal-2026-plane
%X Large Vision-Language Models (LVLMs) commonly suffer from hallucinations, which appear as fabricating non-existent objects or outputting incorrect attributes and spatial relationships in images. Previous works empirically indicate that CLIP-style vision encoders tend to focus on primary objects while ignoring image details, which is one of the causes of hallucinations. To address this issue, we propose plug-and-play fine-grained visual experts (PLANE) comprising two components: LoRA visual experts operating on CLIP for multi-aspect image encoding, and an instruction-aware gate network for adaptive image feature fusion. During training, we construct a fine-grained image-caption pairs dataset, where images are described from three aspects: objects, attributes, and relations between objects. Image-caption pairs from different aspects are used to train the three fine-grained LoRA experts respectively. Aiming at comprehensively evaluate our method’s capabilities, we manually annotate a fine-grained hallucination evaluation benchmark for LVLMs which is GPT4-independent during evaluation phase (GIFT). We conduct experiments both on popular hallucination evaluation benchmarks and GIFT. The results show that our method effectively reduces hallucinations across models of different types and sizes while introducing minimal inference latency. Compared to advanced baselines, our model also demonstrates superior performance.
%U https://aclanthology.org/2026.findings-emnlp.1756/
%P 37559-37576
Markdown (Informal)
[PLANE: Plug-and-Play Fine-Grained Visual Experts for Hallucination Mitigation in Large Vision-Language Models](https://aclanthology.org/2026.findings-emnlp.1756/) (Yin et al., Findings 2026)
ACL