<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lou-etal-2026-rift">
    <titleInfo>
        <title>RIFT: Relation Modeling and Transfer for Visual Figurative Entailment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiaojian</namePart>
        <namePart type="family">Lou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qimeng</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hui</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunjing</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinmiao</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xinjun</namePart>
        <namePart type="family">Pei</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Visual figurative entailment requires determining whether an image supports the nonliteral meaning of a textual claim, posing challenges for multimodal figurative understanding. Existing methods typically use fixed image-text fusion and struggle to capture sample-specific relations between visual evidence and figurative claims. Moreover, the limited scale of annotated visual figurative data makes it difficult to learn robust figurative relations from visual supervision alone. To address these challenges, we propose RIFT, which generates a claim-conditioned visual description and uses a relation-gated multimodal mixture of experts to model interactions among the image, description, and claim. It further retrieves figurative reasoning patterns from a FLUTE-based relation-level rationale memory and employs a confidence routing gate to modulate this external guidance according to retrieval reliability. The resulting internal and external relation representations are integrated as latent prefix tokens for joint entailment prediction and explanation generation. On V-FLUTE, RIFT achieves 88.52 F1@0, 76.07 F1@53, and 59.47 F1@60, outperforming MAPPER by 3.98, 6.38, and 7.75 points, respectively. These improvements, particularly on explanation-constrained metrics, show that relation modeling and cross-modal transfer benefit both prediction and explanation quality.</abstract>
    <identifier type="citekey">lou-etal-2026-rift</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.653/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>13711</start>
            <end>13725</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T RIFT: Relation Modeling and Transfer for Visual Figurative Entailment
%A Lou, Xiaojian
%A Yang, Qimeng
%A Song, Hui
%A Jiang, Yunjing
%A Song, Jinmiao
%A Pei, Xinjun
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F lou-etal-2026-rift
%X Visual figurative entailment requires determining whether an image supports the nonliteral meaning of a textual claim, posing challenges for multimodal figurative understanding. Existing methods typically use fixed image-text fusion and struggle to capture sample-specific relations between visual evidence and figurative claims. Moreover, the limited scale of annotated visual figurative data makes it difficult to learn robust figurative relations from visual supervision alone. To address these challenges, we propose RIFT, which generates a claim-conditioned visual description and uses a relation-gated multimodal mixture of experts to model interactions among the image, description, and claim. It further retrieves figurative reasoning patterns from a FLUTE-based relation-level rationale memory and employs a confidence routing gate to modulate this external guidance according to retrieval reliability. The resulting internal and external relation representations are integrated as latent prefix tokens for joint entailment prediction and explanation generation. On V-FLUTE, RIFT achieves 88.52 F1@0, 76.07 F1@53, and 59.47 F1@60, outperforming MAPPER by 3.98, 6.38, and 7.75 points, respectively. These improvements, particularly on explanation-constrained metrics, show that relation modeling and cross-modal transfer benefit both prediction and explanation quality.
%U https://aclanthology.org/2026.findings-emnlp.653/
%P 13711-13725

Markdown (Informal)

[RIFT: Relation Modeling and Transfer for Visual Figurative Entailment](https://aclanthology.org/2026.findings-emnlp.653/) (Lou et al., Findings 2026)

• RIFT: Relation Modeling and Transfer for Visual Figurative Entailment (Lou et al., Findings 2026)

ACL

• Xiaojian Lou, Qimeng Yang, Hui Song, Yunjing Jiang, Jinmiao Song, and Xinjun Pei. 2026. RIFT: Relation Modeling and Transfer for Visual Figurative Entailment. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 13711–13725, Budapest, Hungary. Association for Computational Linguistics.