@inproceedings{aggarwal-etal-2026-vision,
title = "Can Vision-Language Models Assess Environmental Reporting Compliance? A Benchmark for Requirement-Level Disclosure Alignment",
author = "Aggarwal, Vaishali and
Verma, Ishan and
Gupta, Tanay Kumar and
Dasgupta, Tirthankar",
editor = "Schimanski, Tobias and
Usmanova, Aida and
Morio, Gaku and
Ni, Jingwei and
Dutia, Kalyan and
Vaghefi, Seyed Saeid and
Stammbach, Dominik and
Leippold, Markus",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change ({C}limate{NLP} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.climatenlp-1.20/",
pages = "298--314",
ISBN = "979-8-89176-465-1",
abstract = "Corporate sustainability reports communicate environmental disclosures through text, tables, charts, and infographics, making assessment against sustainability reporting standards challenging. Existing disclosure extraction systems focus on information extraction but do not determine whether disclosed evidence satisfies reporting requirements. We study requirement-level multimodal environmental disclosure alignment, a task that evaluates whether sustainability report evidence satisfies GRI 305 and ESRS E1-4 and E1-6 requirements. To support this task, we curate an expert-annotated benchmark comprising 731 disclosure-alignment instances from 43 sustainability reports. Using this benchmark, we evaluate three Vision Language Models (VLMs): GPT-5.5, Gemini, and LLaMA Maverick under three conditioning strategies: open-ended, framework-specific, and knowledge-augmented. Results show that although frontier VLMs possess substantial implicit knowledge of sustainability reporting standards, they frequently produce over generalized and optimistic alignment judgments. Requirement level grounding improves alignment accuracy by 12{\%} and yields more accurate disclosure gap identification. Our findings demonstrate the value of knowledge grounded multimodal reasoning for scalable, interpretable, and auditable sustainability disclosure assessment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aggarwal-etal-2026-vision">
<titleInfo>
<title>Can Vision-Language Models Assess Environmental Reporting Compliance? A Benchmark for Requirement-Level Disclosure Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vaishali</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ishan</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanay</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Dasgupta</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 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Schimanski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Usmanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalyan</namePart>
<namePart type="family">Dutia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Saeid</namePart>
<namePart type="family">Vaghefi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Stammbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Leippold</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">979-8-89176-465-1</identifier>
</relatedItem>
<abstract>Corporate sustainability reports communicate environmental disclosures through text, tables, charts, and infographics, making assessment against sustainability reporting standards challenging. Existing disclosure extraction systems focus on information extraction but do not determine whether disclosed evidence satisfies reporting requirements. We study requirement-level multimodal environmental disclosure alignment, a task that evaluates whether sustainability report evidence satisfies GRI 305 and ESRS E1-4 and E1-6 requirements. To support this task, we curate an expert-annotated benchmark comprising 731 disclosure-alignment instances from 43 sustainability reports. Using this benchmark, we evaluate three Vision Language Models (VLMs): GPT-5.5, Gemini, and LLaMA Maverick under three conditioning strategies: open-ended, framework-specific, and knowledge-augmented. Results show that although frontier VLMs possess substantial implicit knowledge of sustainability reporting standards, they frequently produce over generalized and optimistic alignment judgments. Requirement level grounding improves alignment accuracy by 12% and yields more accurate disclosure gap identification. Our findings demonstrate the value of knowledge grounded multimodal reasoning for scalable, interpretable, and auditable sustainability disclosure assessment.</abstract>
<identifier type="citekey">aggarwal-etal-2026-vision</identifier>
<location>
<url>https://aclanthology.org/2026.climatenlp-1.20/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>298</start>
<end>314</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Vision-Language Models Assess Environmental Reporting Compliance? A Benchmark for Requirement-Level Disclosure Alignment
%A Aggarwal, Vaishali
%A Verma, Ishan
%A Gupta, Tanay Kumar
%A Dasgupta, Tirthankar
%Y Schimanski, Tobias
%Y Usmanova, Aida
%Y Morio, Gaku
%Y Ni, Jingwei
%Y Dutia, Kalyan
%Y Vaghefi, Seyed Saeid
%Y Stammbach, Dominik
%Y Leippold, Markus
%S Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-465-1
%F aggarwal-etal-2026-vision
%X Corporate sustainability reports communicate environmental disclosures through text, tables, charts, and infographics, making assessment against sustainability reporting standards challenging. Existing disclosure extraction systems focus on information extraction but do not determine whether disclosed evidence satisfies reporting requirements. We study requirement-level multimodal environmental disclosure alignment, a task that evaluates whether sustainability report evidence satisfies GRI 305 and ESRS E1-4 and E1-6 requirements. To support this task, we curate an expert-annotated benchmark comprising 731 disclosure-alignment instances from 43 sustainability reports. Using this benchmark, we evaluate three Vision Language Models (VLMs): GPT-5.5, Gemini, and LLaMA Maverick under three conditioning strategies: open-ended, framework-specific, and knowledge-augmented. Results show that although frontier VLMs possess substantial implicit knowledge of sustainability reporting standards, they frequently produce over generalized and optimistic alignment judgments. Requirement level grounding improves alignment accuracy by 12% and yields more accurate disclosure gap identification. Our findings demonstrate the value of knowledge grounded multimodal reasoning for scalable, interpretable, and auditable sustainability disclosure assessment.
%U https://aclanthology.org/2026.climatenlp-1.20/
%P 298-314
Markdown (Informal)
[Can Vision-Language Models Assess Environmental Reporting Compliance? A Benchmark for Requirement-Level Disclosure Alignment](https://aclanthology.org/2026.climatenlp-1.20/) (Aggarwal et al., ClimateNLP 2026)
ACL