@inproceedings{jia-etal-2025-exploring,
title = "Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models",
author = "Jia, Boyu and
Zhang, Junzhe and
Zhang, Huixuan and
Wan, Xiaojun",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.639/",
doi = "10.18653/v1/2025.findings-emnlp.639",
pages = "11966--11981",
ISBN = "979-8-89176-335-7",
abstract = "In recent years, multimodal large language models (MLLMs) have achieved significant breakthroughs, enhancing understanding across text and vision. However, current MLLMs still face challenges in effectively integrating knowledge across these modalities during multimodal knowledge reasoning, leading to inconsistencies in reasoning outcomes. To systematically explore this issue, we propose four evaluation tasks and construct a new dataset. We conduct a series of experiments on this dataset to analyze and compare the extent of consistency degradation in multimodal knowledge reasoning within MLLMs. Based on the experimental results, we identify factors contributing to the observed degradation in consistency. Our research provides new insights into the challenges of multimodal knowledge reasoning and offers valuable guidance for future efforts aimed at improving MLLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jia-etal-2025-exploring">
<titleInfo>
<title>Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boyu</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junzhe</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huixuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>In recent years, multimodal large language models (MLLMs) have achieved significant breakthroughs, enhancing understanding across text and vision. However, current MLLMs still face challenges in effectively integrating knowledge across these modalities during multimodal knowledge reasoning, leading to inconsistencies in reasoning outcomes. To systematically explore this issue, we propose four evaluation tasks and construct a new dataset. We conduct a series of experiments on this dataset to analyze and compare the extent of consistency degradation in multimodal knowledge reasoning within MLLMs. Based on the experimental results, we identify factors contributing to the observed degradation in consistency. Our research provides new insights into the challenges of multimodal knowledge reasoning and offers valuable guidance for future efforts aimed at improving MLLMs.</abstract>
<identifier type="citekey">jia-etal-2025-exploring</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.639</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.639/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>11966</start>
<end>11981</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models
%A Jia, Boyu
%A Zhang, Junzhe
%A Zhang, Huixuan
%A Wan, Xiaojun
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F jia-etal-2025-exploring
%X In recent years, multimodal large language models (MLLMs) have achieved significant breakthroughs, enhancing understanding across text and vision. However, current MLLMs still face challenges in effectively integrating knowledge across these modalities during multimodal knowledge reasoning, leading to inconsistencies in reasoning outcomes. To systematically explore this issue, we propose four evaluation tasks and construct a new dataset. We conduct a series of experiments on this dataset to analyze and compare the extent of consistency degradation in multimodal knowledge reasoning within MLLMs. Based on the experimental results, we identify factors contributing to the observed degradation in consistency. Our research provides new insights into the challenges of multimodal knowledge reasoning and offers valuable guidance for future efforts aimed at improving MLLMs.
%R 10.18653/v1/2025.findings-emnlp.639
%U https://aclanthology.org/2025.findings-emnlp.639/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.639
%P 11966-11981
Markdown (Informal)
[Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models](https://aclanthology.org/2025.findings-emnlp.639/) (Jia et al., Findings 2025)
ACL