<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muszynski-etal-2026-mllm">
    <titleInfo>
        <title>mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jakub</namePart>
        <namePart type="family">Muszyński</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paweł</namePart>
        <namePart type="family">Pozorski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maria</namePart>
        <namePart type="family">Ganzha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Greg</namePart>
            <namePart type="family">Durrett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ping</namePart>
            <namePart type="family">Jian</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-392-0</identifier>
    </relatedItem>
    <abstract>We present mllm-shap, an open-sourcePython platform for researchers and ML practitioners that extends Shapley value (SV)explainability from text-only large languagemodels to multimodal LLMs (MLLMs) thatjointly process text and audio. Buildingon the token-level SV framework introducedby TokenSHAP, mllm-shap addresses threechallenges absent in the text-only setting:(1) modality-aware coalition masking thathandles the coexistence of text tokens anddense audio encoder frames within a single input, (2) multi-turn conversation tracking withper-token role and modality metadata, and(3) audio token grouping via phonetic alignment that reduces the coalition space by 10–50 times. The platform ships as a pip-installablepackage implementing five SV estimation strategies – including a Complementary Contributions estimator with Neyman-optimal allocation that outperforms Monte Carlo baselines – together with an interactive web GUIfor real-time attribution visualization. Toour knowledge, mllm-shap is the first publicly available framework for complete, reproducible SV-based explainability of text-audioMLLMs. The package is MIT-licensed withfull source code on GitHub and a demonstration video included as supplementary material.</abstract>
    <identifier type="citekey">muszynski-etal-2026-mllm</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-demo.38/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>387</start>
            <end>396</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models
%A Muszyński, Jakub
%A Pozorski, Paweł
%A Ganzha, Maria
%Y Durrett, Greg
%Y Jian, Ping
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-392-0
%F muszynski-etal-2026-mllm
%X We present mllm-shap, an open-sourcePython platform for researchers and ML practitioners that extends Shapley value (SV)explainability from text-only large languagemodels to multimodal LLMs (MLLMs) thatjointly process text and audio. Buildingon the token-level SV framework introducedby TokenSHAP, mllm-shap addresses threechallenges absent in the text-only setting:(1) modality-aware coalition masking thathandles the coexistence of text tokens anddense audio encoder frames within a single input, (2) multi-turn conversation tracking withper-token role and modality metadata, and(3) audio token grouping via phonetic alignment that reduces the coalition space by 10–50 times. The platform ships as a pip-installablepackage implementing five SV estimation strategies – including a Complementary Contributions estimator with Neyman-optimal allocation that outperforms Monte Carlo baselines – together with an interactive web GUIfor real-time attribution visualization. Toour knowledge, mllm-shap is the first publicly available framework for complete, reproducible SV-based explainability of text-audioMLLMs. The package is MIT-licensed withfull source code on GitHub and a demonstration video included as supplementary material.
%U https://aclanthology.org/2026.acl-demo.38/
%P 387-396

Markdown (Informal)

[mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models](https://aclanthology.org/2026.acl-demo.38/) (Muszyński et al., ACL 2026)

• mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models (Muszyński et al., ACL 2026)

ACL

• Jakub Muszyński, Paweł Pozorski, and Maria Ganzha. 2026. mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 387–396, San Diego, California, United States. Association for Computational Linguistics.