@inproceedings{dong-etal-2024-modality,
title = "Modality-Aware Integration with Large Language Models for Knowledge-Based Visual Question Answering",
author = "Dong, Junnan and
Zhang, Qinggang and
Zhou, Huachi and
Zha, Daochen and
Zheng, Pai and
Huang, Xiao",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.132",
pages = "2417--2429",
abstract = "Knowledge-based visual question answering (KVQA) has been extensively studied to answer visual questions with external knowledge, e.g., knowledge graphs (KGs). While several attempts have been proposed to leverage large language models (LLMs) as an implicit knowledge source, it remains challenging since LLMs may generate hallucinations. Moreover, multiple knowledge sources, e.g., images, KGs and LLMs, cannot be readily aligned for complex scenarios. To tackle these, we present a novel modality-aware integration with LLMs for KVQA ($\texttt{MAIL}$). It carefully leverages multimodal knowledge for both image understanding and knowledge reasoning. Specifically, $(i)$ we propose a two-stage prompting strategy with LLMs to densely embody the image into a *scene graph* with detailed visual features; $(ii)$ We construct a coupled *concept graph* by linking the mentioned entities with external facts. $(iii)$ A tailored pseudo-siamese graph medium fusion is designed for sufficient multimodal fusion. We utilize the shared mentioned entities in two graphs as mediums to bridge a tight inter-modal exchange, while maximally preserving insightful intra-modal learning by constraining the fusion within mediums. Extensive experiments show the superiority of $\texttt{MAIL}$.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2024-modality">
<titleInfo>
<title>Modality-Aware Integration with Large Language Models for Knowledge-Based Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junnan</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qinggang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huachi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daochen</namePart>
<namePart type="family">Zha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pai</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge-based visual question answering (KVQA) has been extensively studied to answer visual questions with external knowledge, e.g., knowledge graphs (KGs). While several attempts have been proposed to leverage large language models (LLMs) as an implicit knowledge source, it remains challenging since LLMs may generate hallucinations. Moreover, multiple knowledge sources, e.g., images, KGs and LLMs, cannot be readily aligned for complex scenarios. To tackle these, we present a novel modality-aware integration with LLMs for KVQA (MAIL). It carefully leverages multimodal knowledge for both image understanding and knowledge reasoning. Specifically, (i) we propose a two-stage prompting strategy with LLMs to densely embody the image into a *scene graph* with detailed visual features; (ii) We construct a coupled *concept graph* by linking the mentioned entities with external facts. (iii) A tailored pseudo-siamese graph medium fusion is designed for sufficient multimodal fusion. We utilize the shared mentioned entities in two graphs as mediums to bridge a tight inter-modal exchange, while maximally preserving insightful intra-modal learning by constraining the fusion within mediums. Extensive experiments show the superiority of MAIL.</abstract>
<identifier type="citekey">dong-etal-2024-modality</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.132</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2417</start>
<end>2429</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modality-Aware Integration with Large Language Models for Knowledge-Based Visual Question Answering
%A Dong, Junnan
%A Zhang, Qinggang
%A Zhou, Huachi
%A Zha, Daochen
%A Zheng, Pai
%A Huang, Xiao
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F dong-etal-2024-modality
%X Knowledge-based visual question answering (KVQA) has been extensively studied to answer visual questions with external knowledge, e.g., knowledge graphs (KGs). While several attempts have been proposed to leverage large language models (LLMs) as an implicit knowledge source, it remains challenging since LLMs may generate hallucinations. Moreover, multiple knowledge sources, e.g., images, KGs and LLMs, cannot be readily aligned for complex scenarios. To tackle these, we present a novel modality-aware integration with LLMs for KVQA (MAIL). It carefully leverages multimodal knowledge for both image understanding and knowledge reasoning. Specifically, (i) we propose a two-stage prompting strategy with LLMs to densely embody the image into a *scene graph* with detailed visual features; (ii) We construct a coupled *concept graph* by linking the mentioned entities with external facts. (iii) A tailored pseudo-siamese graph medium fusion is designed for sufficient multimodal fusion. We utilize the shared mentioned entities in two graphs as mediums to bridge a tight inter-modal exchange, while maximally preserving insightful intra-modal learning by constraining the fusion within mediums. Extensive experiments show the superiority of MAIL.
%U https://aclanthology.org/2024.acl-long.132
%P 2417-2429
Markdown (Informal)
[Modality-Aware Integration with Large Language Models for Knowledge-Based Visual Question Answering](https://aclanthology.org/2024.acl-long.132) (Dong et al., ACL 2024)
ACL