<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2026-object">
    <titleInfo>
        <title>Object Presence Is Not Relation Evidence: Relation-Grounded Faithful Reasoning for Multimodal Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiyao</namePart>
        <namePart type="family">Dong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yilong</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaojin</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kun</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Recent Multimodal Large Language Models (MLLMs) excel in precise entity recognition and powerful reasoning, significantly boosting performance and efficiency in complex vision-language tasks. Despite these gains, this advanced reasoning process introduces a subtle yet critical vulnerability. We identify an underexplored relational reasoning failure mode in which models over-prioritize semantic coherence, thereby inferring ungrounded interactions from mere object entities. We term this phenomenon Relation Evidence Amnesia (REA), wherein MLLMs correctly localize individual entities but fail to enforce true visual dependencies as the generative process becomes hijacked by semantic rationalization. To mitigate REA, we propose Relation-Grounded Faithful Reasoning (RGFR), an inference-time decoding intervention that operates without modifying target model parameters. Adopting a decoupled verification philosophy, RGFR employs a semantic-driven soft-gating mechanism to simultaneously incorporate explicit entity constraints and extract counterfactual causal evidence, followed by a Unified Schema-Aware Rectifier that rigorously mediates these visual-causal constraints during the decoding process. Extensive experiments across relation benchmarks demonstrate that RGFR improves relation recognition accuracy by over 8.1% compared to baselines, while largely preserving task utility. These results highlight the critical role of decoupled, evidence-grounded rectification in achieving faithful relational reasoning for multimodal models.</abstract>
    <identifier type="citekey">dong-etal-2026-object</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1418/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>32379</start>
            <end>32395</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Object Presence Is Not Relation Evidence: Relation-Grounded Faithful Reasoning for Multimodal Large Language Models
%A Dong, Xiyao
%A Chen, Yilong
%A Zhang, Xiaojin
%A He, Kun
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F dong-etal-2026-object
%X Recent Multimodal Large Language Models (MLLMs) excel in precise entity recognition and powerful reasoning, significantly boosting performance and efficiency in complex vision-language tasks. Despite these gains, this advanced reasoning process introduces a subtle yet critical vulnerability. We identify an underexplored relational reasoning failure mode in which models over-prioritize semantic coherence, thereby inferring ungrounded interactions from mere object entities. We term this phenomenon Relation Evidence Amnesia (REA), wherein MLLMs correctly localize individual entities but fail to enforce true visual dependencies as the generative process becomes hijacked by semantic rationalization. To mitigate REA, we propose Relation-Grounded Faithful Reasoning (RGFR), an inference-time decoding intervention that operates without modifying target model parameters. Adopting a decoupled verification philosophy, RGFR employs a semantic-driven soft-gating mechanism to simultaneously incorporate explicit entity constraints and extract counterfactual causal evidence, followed by a Unified Schema-Aware Rectifier that rigorously mediates these visual-causal constraints during the decoding process. Extensive experiments across relation benchmarks demonstrate that RGFR improves relation recognition accuracy by over 8.1% compared to baselines, while largely preserving task utility. These results highlight the critical role of decoupled, evidence-grounded rectification in achieving faithful relational reasoning for multimodal models.
%U https://aclanthology.org/2026.emnlp-main.1418/
%P 32379-32395

Markdown (Informal)

[Object Presence Is Not Relation Evidence: Relation-Grounded Faithful Reasoning for Multimodal Large Language Models](https://aclanthology.org/2026.emnlp-main.1418/) (Dong et al., EMNLP 2026)

• Object Presence Is Not Relation Evidence: Relation-Grounded Faithful Reasoning for Multimodal Large Language Models (Dong et al., EMNLP 2026)

ACL

• Xiyao Dong, Yilong Chen, Xiaojin Zhang, and Kun He. 2026. Object Presence Is Not Relation Evidence: Relation-Grounded Faithful Reasoning for Multimodal Large Language Models. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 32379–32395, Budapest, Hungary. Association for Computational Linguistics.