Assessing corporate sustainability with large language models: evidence from Europe
大規模言語モデルを用いた企業のサステナビリティ評価：欧州のエビデンス (AI 翻訳)
Kerstin Forster, Lucas Keil, Victor Wagner, Maximilian A. Müller, Thorsten Sellhorn, S. Feuerriegel
🤖 gxceed AI 要約
日本語
本論文は、大規模言語モデルを用いて600社の欧州企業の報告書からESG指標を抽出する枠組みを開発。開示ギャップの存在と縮小傾向、Scope 3排出量の増加（開示改善に起因）などを明らかにした。性能は環境指標で改善、社会指標は停滞。オープンソースで提供。
English
This paper develops a machine learning framework to extract ESG indicators from corporate reports, applied to 600 large European firms (2014-2023). It reveals a transparency gap between high and low ESG-rated firms, narrowing over time, and uneven performance: environmental indicators improve while social indicators stagnate. Scope 3 emissions increase sharply due to better disclosure. The open-source framework enables systematic ESG tracking.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
欧州企業を対象とするが、手法は日本企業にも応用可能。SSBJの開示基準や有報でのESG情報拡充に活用できる。AIによるESGデータ抽出は、日本の企業の開示負担軽減に寄与する可能性がある。
In the global GX context
This paper shows how AI can systematically extract ESG data from corporate reports, addressing a key challenge for global disclosure frameworks like ISSB and CSRD. It provides a scalable tool for tracking ESG transparency and performance across firms, relevant for investors and regulators worldwide.
👥 読者別の含意
🔬研究者:Researchers can adopt this open-source framework to build large-scale ESG datasets and analyze disclosure patterns across regions.
🏢実務担当者:Corporate sustainability teams can use this to benchmark their ESG disclosure against peers and identify gaps.
🏛政策担当者:Policymakers can leverage this framework to monitor the effectiveness of disclosure regulations and assess corporate sustainability progress.
📄 Abstract（原文）
Companies play a crucial role in achieving global sustainability goals, yet evidence on their progress across environmental, social, and governance (ESG) dimensions remains limited. We develop a machine learning framework to systematically extract ESG indicators from corporate reports. Applying this approach to annual and sustainability reports of 600 large European firms (2014–2023), we construct a dataset of 2.9 million ESG observations across environmental, social, and governance topics. We assess ESG transparency based on disclosures aligned with the European Sustainability Reporting Standards (ESRS) and evaluate ESG performance using extracted numerical indicators. Results reveal a pronounced transparency gap: firms in the top ESG rating decile disclose 22% more indicators than those in the bottom decile, although this gap narrows over time. Performance trends are uneven: while most social indicators remain largely stagnant, except for gains in gender equality, environmental indicators show some improvement. Reported scope 3 emissions increase sharply, largely reflecting improved disclosure. Our open-source framework enables systematic tracking of corporate ESG efforts. This study uses machine learning to extract environmental, social, and governance (ESG) indicators from corporate reports of 600 large European firms, revealing a pronounced but narrowing disclosure gap and uneven ESG performance.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://www.nature.com/articles/s41467-026-75160-z.pdffirst seen 2026-07-18 07:28:53
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。