@inproceedings{ye-etal-2025-knowledge,
title = "Knowledge Image Matters: Improving Knowledge-Based Visual Reasoning with Multi-Image Large Language Models",
author = "Ye, Guanghui and
Zhao, Huan and
Zhao, Zhixue and
Zha, Xupeng and
Liu, Yang and
Jiang, Zhihua",
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.1063/",
doi = "10.18653/v1/2025.acl-long.1063",
pages = "21883--21896",
ISBN = "979-8-89176-251-0",
abstract = "We revisit knowledge-based visual reasoning (KB-VR) in light of modern advances in multimodal large language models (MLLMs), and make the following contributions: (i) We propose Visual Knowledge Card (VKC) {--} a novel image that incorporates not only internal visual knowledge (e.g., scene-aware information) detected from the raw image, but also external world knowledge (e.g., attribute or object knowledge) produced by a knowledge generator; (ii) We present VKC-based Multi-Image Reasoning (VKC-MIR) {--} a four-stage pipeline which harnesses a state-of-the-art scene perception engine to construct an initial VKC (Stage-1), a powerful LLM to generate relevant domain knowledge (Stage-2), an excellent image editing toolkit to introduce generated knowledge into the updated VKC (Stage-3), and finally, an emerging multi-image MLLM to solve the VKC-enhanced task (Stage-4). By performing experiments on three popular KB-VR benchmarks, our approach achieves new state-of-the-art results compared to previous top-performing models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ye-etal-2025-knowledge">
<titleInfo>
<title>Knowledge Image Matters: Improving Knowledge-Based Visual Reasoning with Multi-Image Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guanghui</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhixue</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xupeng</namePart>
<namePart type="family">Zha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihua</namePart>
<namePart type="family">Jiang</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>We revisit knowledge-based visual reasoning (KB-VR) in light of modern advances in multimodal large language models (MLLMs), and make the following contributions: (i) We propose Visual Knowledge Card (VKC) – a novel image that incorporates not only internal visual knowledge (e.g., scene-aware information) detected from the raw image, but also external world knowledge (e.g., attribute or object knowledge) produced by a knowledge generator; (ii) We present VKC-based Multi-Image Reasoning (VKC-MIR) – a four-stage pipeline which harnesses a state-of-the-art scene perception engine to construct an initial VKC (Stage-1), a powerful LLM to generate relevant domain knowledge (Stage-2), an excellent image editing toolkit to introduce generated knowledge into the updated VKC (Stage-3), and finally, an emerging multi-image MLLM to solve the VKC-enhanced task (Stage-4). By performing experiments on three popular KB-VR benchmarks, our approach achieves new state-of-the-art results compared to previous top-performing models.</abstract>
<identifier type="citekey">ye-etal-2025-knowledge</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1063</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1063/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>21883</start>
<end>21896</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Image Matters: Improving Knowledge-Based Visual Reasoning with Multi-Image Large Language Models
%A Ye, Guanghui
%A Zhao, Huan
%A Zhao, Zhixue
%A Zha, Xupeng
%A Liu, Yang
%A Jiang, Zhihua
%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 ye-etal-2025-knowledge
%X We revisit knowledge-based visual reasoning (KB-VR) in light of modern advances in multimodal large language models (MLLMs), and make the following contributions: (i) We propose Visual Knowledge Card (VKC) – a novel image that incorporates not only internal visual knowledge (e.g., scene-aware information) detected from the raw image, but also external world knowledge (e.g., attribute or object knowledge) produced by a knowledge generator; (ii) We present VKC-based Multi-Image Reasoning (VKC-MIR) – a four-stage pipeline which harnesses a state-of-the-art scene perception engine to construct an initial VKC (Stage-1), a powerful LLM to generate relevant domain knowledge (Stage-2), an excellent image editing toolkit to introduce generated knowledge into the updated VKC (Stage-3), and finally, an emerging multi-image MLLM to solve the VKC-enhanced task (Stage-4). By performing experiments on three popular KB-VR benchmarks, our approach achieves new state-of-the-art results compared to previous top-performing models.
%R 10.18653/v1/2025.acl-long.1063
%U https://aclanthology.org/2025.acl-long.1063/
%U https://doi.org/10.18653/v1/2025.acl-long.1063
%P 21883-21896
Markdown (Informal)
[Knowledge Image Matters: Improving Knowledge-Based Visual Reasoning with Multi-Image Large Language Models](https://aclanthology.org/2025.acl-long.1063/) (Ye et al., ACL 2025)
ACL