@inproceedings{he-etal-2026-mm,
title = "{MM}-{COMPLIANCE}: A Multilingual Multimodal Dataset for Sustainability Compliance Auditing",
author = {He, Rui and
Yang, Jianhua and
Kera, Tomoki and
Keyaki, Atsushi and
Lhuissier, Ana{\"i}s and
Kang, Juyeon and
Day, Min-Yuh and
Yang, Guan-Bo and
Chen, Hsin-Hsi and
Wanvarie, Dittaya and
Lee, Yongjae and
Park, Suhwan and
Nakao, Yuriko and
Chen, Chung-Chi and
Seki, Yohei},
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.802/",
pages = "18675--18690",
ISBN = "979-8-89176-459-0",
abstract = "Detecting whether corporate sustainability disclosures truly satisfy reporting standards is essential for greenwashing-aware ESG auditing, yet existing resources rarely evaluate whether disclosures sufficiently satisfy framework metrics. We introduce MM-COMPLIANCE, a multilingual multimodal dataset aligned with SASB metrics across six languages (English, French, Japanese, Chinese, Thai, and Korean), with page-level evidence and a key completeness annotation that separates fully compliant disclosures from partial mentions. We define two tasks reflecting practical auditing workflows: Page-level Compliance Judgment and Metric-to-Page Evidence Retrieval. Our evaluated baselines primarily comprising open-source architectures, supplemented by a commercial VLM as an upper-bound reference, show moderate performance for page understanding and evidence localization, but consistently low performance on partial compliance verification and large variation across languages and industries. MM-COMPLIANCE provides a benchmark for developing framework-aware models to support rigorous ESG compliance auditing and long-term commitment tracing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2026-mm">
<titleInfo>
<title>MM-COMPLIANCE: A Multilingual Multimodal Dataset for Sustainability Compliance Auditing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianhua</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoki</namePart>
<namePart type="family">Kera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Keyaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Lhuissier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juyeon</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yuh</namePart>
<namePart type="family">Day</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guan-Bo</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dittaya</namePart>
<namePart type="family">Wanvarie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suhwan</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuriko</namePart>
<namePart type="family">Nakao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohei</namePart>
<namePart type="family">Seki</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>Detecting whether corporate sustainability disclosures truly satisfy reporting standards is essential for greenwashing-aware ESG auditing, yet existing resources rarely evaluate whether disclosures sufficiently satisfy framework metrics. We introduce MM-COMPLIANCE, a multilingual multimodal dataset aligned with SASB metrics across six languages (English, French, Japanese, Chinese, Thai, and Korean), with page-level evidence and a key completeness annotation that separates fully compliant disclosures from partial mentions. We define two tasks reflecting practical auditing workflows: Page-level Compliance Judgment and Metric-to-Page Evidence Retrieval. Our evaluated baselines primarily comprising open-source architectures, supplemented by a commercial VLM as an upper-bound reference, show moderate performance for page understanding and evidence localization, but consistently low performance on partial compliance verification and large variation across languages and industries. MM-COMPLIANCE provides a benchmark for developing framework-aware models to support rigorous ESG compliance auditing and long-term commitment tracing.</abstract>
<identifier type="citekey">he-etal-2026-mm</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.802/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>18675</start>
<end>18690</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MM-COMPLIANCE: A Multilingual Multimodal Dataset for Sustainability Compliance Auditing
%A He, Rui
%A Yang, Jianhua
%A Kera, Tomoki
%A Keyaki, Atsushi
%A Lhuissier, Anaïs
%A Kang, Juyeon
%A Day, Min-Yuh
%A Yang, Guan-Bo
%A Chen, Hsin-Hsi
%A Wanvarie, Dittaya
%A Lee, Yongjae
%A Park, Suhwan
%A Nakao, Yuriko
%A Chen, Chung-Chi
%A Seki, Yohei
%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 he-etal-2026-mm
%X Detecting whether corporate sustainability disclosures truly satisfy reporting standards is essential for greenwashing-aware ESG auditing, yet existing resources rarely evaluate whether disclosures sufficiently satisfy framework metrics. We introduce MM-COMPLIANCE, a multilingual multimodal dataset aligned with SASB metrics across six languages (English, French, Japanese, Chinese, Thai, and Korean), with page-level evidence and a key completeness annotation that separates fully compliant disclosures from partial mentions. We define two tasks reflecting practical auditing workflows: Page-level Compliance Judgment and Metric-to-Page Evidence Retrieval. Our evaluated baselines primarily comprising open-source architectures, supplemented by a commercial VLM as an upper-bound reference, show moderate performance for page understanding and evidence localization, but consistently low performance on partial compliance verification and large variation across languages and industries. MM-COMPLIANCE provides a benchmark for developing framework-aware models to support rigorous ESG compliance auditing and long-term commitment tracing.
%U https://aclanthology.org/2026.emnlp-main.802/
%P 18675-18690
Markdown (Informal)
[MM-COMPLIANCE: A Multilingual Multimodal Dataset for Sustainability Compliance Auditing](https://aclanthology.org/2026.emnlp-main.802/) (He et al., EMNLP 2026)
ACL
- Rui He, Jianhua Yang, Tomoki Kera, Atsushi Keyaki, Anaïs Lhuissier, Juyeon Kang, Min-Yuh Day, Guan-Bo Yang, Hsin-Hsi Chen, Dittaya Wanvarie, Yongjae Lee, Suhwan Park, Yuriko Nakao, Chung-Chi Chen, and Yohei Seki. 2026. MM-COMPLIANCE: A Multilingual Multimodal Dataset for Sustainability Compliance Auditing. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 18675–18690, Budapest, Hungary. Association for Computational Linguistics.