<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-magic">
    <titleInfo>
        <title>MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shuo</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Caren</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Siwen</namePart>
        <namePart type="family">Luo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eduard</namePart>
        <namePart type="family">Hovy</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Visual Question Answering (VQA) necessitates models to reason effectively across visual and textual modalities. However, existing Large Vision-Language Models (LVLMs) often fall short in achieving human-like reasoning due to a lack of integrated commonsense knowledge, limiting their robustness and accuracy in real-world scenarios where both explicit facts and implicit understanding are crucial. To address this challenge, we present MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge, a novel framework designed to enhance multimodal inference by integrating commonsense reasoning. MAGIC-VQA introduces a three-stage process: (1) Explicit Commonsense Knowledge Retrieval from external knowledge graphs, (2) By-Type Commonsense Knowledge Post-Processing to refine contextual relevance, and (3) Implicit Commonsense Knowledge Augmentation using a heterogeneous graph processed by a Graph Neural Network (GNN). These stages collectively enable nuanced, context-aware reasoning without extensive pre-training or intricate prompt tuning.Our MAGIC-VQA significantly improves comprehensive benchmark datasets, surpassing existing models in tasks requiring advanced commonsense reasoning. MAGIC-VQA establishes a robust pathway for integrating commonsense knowledge into VQA, bridging the gap between vision-language inputs and high-level reasoning for improved reliability and contextual accuracy.</abstract>
    <identifier type="citekey">yang-etal-2025-magic</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.872</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.872/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>16967</start>
            <end>16986</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering
%A Yang, Shuo
%A Han, Caren
%A Luo, Siwen
%A Hovy, Eduard
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F yang-etal-2025-magic
%X Visual Question Answering (VQA) necessitates models to reason effectively across visual and textual modalities. However, existing Large Vision-Language Models (LVLMs) often fall short in achieving human-like reasoning due to a lack of integrated commonsense knowledge, limiting their robustness and accuracy in real-world scenarios where both explicit facts and implicit understanding are crucial. To address this challenge, we present MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge, a novel framework designed to enhance multimodal inference by integrating commonsense reasoning. MAGIC-VQA introduces a three-stage process: (1) Explicit Commonsense Knowledge Retrieval from external knowledge graphs, (2) By-Type Commonsense Knowledge Post-Processing to refine contextual relevance, and (3) Implicit Commonsense Knowledge Augmentation using a heterogeneous graph processed by a Graph Neural Network (GNN). These stages collectively enable nuanced, context-aware reasoning without extensive pre-training or intricate prompt tuning.Our MAGIC-VQA significantly improves comprehensive benchmark datasets, surpassing existing models in tasks requiring advanced commonsense reasoning. MAGIC-VQA establishes a robust pathway for integrating commonsense knowledge into VQA, bridging the gap between vision-language inputs and high-level reasoning for improved reliability and contextual accuracy.
%R 10.18653/v1/2025.findings-acl.872
%U https://aclanthology.org/2025.findings-acl.872/
%U https://doi.org/10.18653/v1/2025.findings-acl.872
%P 16967-16986

Markdown (Informal)

[MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering](https://aclanthology.org/2025.findings-acl.872/) (Yang et al., Findings 2025)

• MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering (Yang et al., Findings 2025)

ACL

• Shuo Yang, Caren Han, Siwen Luo, and Eduard Hovy. 2025. MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering. In Findings of the Association for Computational Linguistics: ACL 2025, pages 16967–16986, Vienna, Austria. Association for Computational Linguistics.