@inproceedings{ahmed-etal-2026-esg,
title = "{ESG}-{CID}-Plus: A Stratified Benchmark for Disclosure Content Index Table Extraction from Corporate Sustainability Reports",
author = "Ahmed, Shafiuddin Rehan and
Abdi, Reza and
Luan, Tianyu and
Kanchinadam, Teja and
Clarke, Christopher and
Siow, Eugene",
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-1.14/",
pages = "183--198",
ISBN = "979-8-89176-465-1",
abstract = "Corporate sustainability reports include a \textit{content index} mapping each disclosure required by a reporting framework (e.g. GRI) to its supporting pages {---} a resource that potentially benefits nearly every downstream sustainability-NLP task, yet no existing benchmark scores its recovery as a framework-grounded, page-resolved output. We formalize Content Index Detection (CID) as three evaluable stages {---} index page retrieval (S1), table extraction and disclosure linking (S2), and page-label-to-index resolution (S3) {---} and release \texttt{esg{\_}cid{\_}plus}: 37 GRI reports and 7{,}294 rows stratified across three difficulty tiers, from unchanged real reports to an adversarial tier of naturally hard documents and synthetic perturbations. Our main benchmark sweeps open-weight vision-language models from sub-1B to 35B parameters (plus frontier-API references) as S2 extractors under shared, deterministic S1 and S3 stages: the best backends reach S2-F1 of 0.89{--}0.92 on the easier tiers, while standard OCR-benchmark scores explain only a third of the variance in extraction quality. Composing extraction with the deterministic resolver exposes S3 as the open frontier: under label-scheme resolution alone, where even best extraction caps end-to-end F1 at 0.11 on the hardest tier. \texttt{esg{\_}cid{\_}plus} will be released in huggingface."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmed-etal-2026-esg">
<titleInfo>
<title>ESG-CID-Plus: A Stratified Benchmark for Disclosure Content Index Table Extraction from Corporate Sustainability Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shafiuddin</namePart>
<namePart type="given">Rehan</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Abdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Luan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teja</namePart>
<namePart type="family">Kanchinadam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Clarke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Siow</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 include a content index mapping each disclosure required by a reporting framework (e.g. GRI) to its supporting pages — a resource that potentially benefits nearly every downstream sustainability-NLP task, yet no existing benchmark scores its recovery as a framework-grounded, page-resolved output. We formalize Content Index Detection (CID) as three evaluable stages — index page retrieval (S1), table extraction and disclosure linking (S2), and page-label-to-index resolution (S3) — and release esg_cid_plus: 37 GRI reports and 7,294 rows stratified across three difficulty tiers, from unchanged real reports to an adversarial tier of naturally hard documents and synthetic perturbations. Our main benchmark sweeps open-weight vision-language models from sub-1B to 35B parameters (plus frontier-API references) as S2 extractors under shared, deterministic S1 and S3 stages: the best backends reach S2-F1 of 0.89–0.92 on the easier tiers, while standard OCR-benchmark scores explain only a third of the variance in extraction quality. Composing extraction with the deterministic resolver exposes S3 as the open frontier: under label-scheme resolution alone, where even best extraction caps end-to-end F1 at 0.11 on the hardest tier. esg_cid_plus will be released in huggingface.</abstract>
<identifier type="citekey">ahmed-etal-2026-esg</identifier>
<location>
<url>https://aclanthology.org/2026.climatenlp-1.14/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>183</start>
<end>198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ESG-CID-Plus: A Stratified Benchmark for Disclosure Content Index Table Extraction from Corporate Sustainability Reports
%A Ahmed, Shafiuddin Rehan
%A Abdi, Reza
%A Luan, Tianyu
%A Kanchinadam, Teja
%A Clarke, Christopher
%A Siow, Eugene
%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 ahmed-etal-2026-esg
%X Corporate sustainability reports include a content index mapping each disclosure required by a reporting framework (e.g. GRI) to its supporting pages — a resource that potentially benefits nearly every downstream sustainability-NLP task, yet no existing benchmark scores its recovery as a framework-grounded, page-resolved output. We formalize Content Index Detection (CID) as three evaluable stages — index page retrieval (S1), table extraction and disclosure linking (S2), and page-label-to-index resolution (S3) — and release esg_cid_plus: 37 GRI reports and 7,294 rows stratified across three difficulty tiers, from unchanged real reports to an adversarial tier of naturally hard documents and synthetic perturbations. Our main benchmark sweeps open-weight vision-language models from sub-1B to 35B parameters (plus frontier-API references) as S2 extractors under shared, deterministic S1 and S3 stages: the best backends reach S2-F1 of 0.89–0.92 on the easier tiers, while standard OCR-benchmark scores explain only a third of the variance in extraction quality. Composing extraction with the deterministic resolver exposes S3 as the open frontier: under label-scheme resolution alone, where even best extraction caps end-to-end F1 at 0.11 on the hardest tier. esg_cid_plus will be released in huggingface.
%U https://aclanthology.org/2026.climatenlp-1.14/
%P 183-198
Markdown (Informal)
[ESG-CID-Plus: A Stratified Benchmark for Disclosure Content Index Table Extraction from Corporate Sustainability Reports](https://aclanthology.org/2026.climatenlp-1.14/) (Ahmed et al., ClimateNLP 2026)
ACL