Sustainalyze: AI Powered Transperancy in ESG Reporting
Sustainalyze: ESG報告におけるAI駆動の透明性 (AI 翻訳)
Kunj Modh, Varun Patel, Vivek Devani
🤖 gxceed AI 要約
日本語
本論文は、ESG報告書の自動分析のためのAI駆動プラットフォームを提案する。RAGアプローチを用いてテキストと表形式データからESG指標を抽出し、FinBERT-ESGで分類、ChromaDBで意味検索、LLMで文脈に応じた抽出を行う。リスクスコアとインパクトスコアの2つのESGスコアを生成し、マルチシグナルグリーンウォッシング検出機構を組み込む。これにより、ESG分析の精度、透明性、拡張性が向上し、意思決定のための証拠に基づく洞察を提供する。
English
This paper presents an AI-powered platform for automated analysis of ESG reports. It uses a Retrieval-Augmented Generation (RAG) approach to extract ESG metrics from text and tables, integrating FinBERT-ESG for classification, ChromaDB for semantic retrieval, and LLMs for context-aware extraction. The platform generates dual ESG scores (Risk and Impact) and incorporates a multi-signal greenwashing detection mechanism. It improves accuracy, transparency, and scalability in ESG analysis, providing evidence-based insights for decision-making.
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
日本ではSSBJ基準の適用が進み、ESG報告の質と透明性が求められている。本システムは、膨大な報告書から自動的に指標を抽出し、グリーンウォッシングを検出することで、投資家や規制当局の信頼性向上に貢献する可能性がある。日本の企業がグローバルな開示基準に対応する際の支援ツールとしても有用である。
In the global GX context
With global ESG disclosure mandates like CSRD, SEC climate rule, and ISSB standards expanding, automated analysis and greenwashing detection are increasingly critical. This platform offers a scalable solution to efficiently process large, unstructured reports, extract key metrics, and identify misleading claims. It addresses the growing need for transparency and comparability in ESG data, supporting investors, regulators, and companies.
👥 読者別の含意
🔬研究者:This paper demonstrates a novel combination of RAG, FinBERT-ESG, and LLMs for ESG metric extraction and greenwashing detection, offering a foundation for further research in AI-driven sustainability analysis.
🏢実務担当者:Corporate sustainability teams can leverage this platform to automate ESG report analysis, generate dual scores, and detect potential greenwashing, enhancing reporting efficiency and credibility.
🏛政策担当者:Regulators can use the greenwashing detection mechanism as a reference for developing automated oversight tools to ensure compliance with ESG disclosure standards.
📄 Abstract（原文）
This work presents ESG Analytics, an AI-powered platform for automated analysis of Environmental, Social, and Governance (ESG) reports. ESG reports are often large, complex, and unstructured, making manual analysis inefficient and time-consuming. The proposed system uses a Retrieval-Augmented Generation (RAG) approach to extract ESG metrics from both textual and tabular data. It integrates FinBERT-ESG for classification, ChromaDB for semantic retrieval, and Large Language Models (LLMs) for accurate and context-aware extraction. The platform generates dual ESG scores, including Risk Score and Impact Score, and incorporates a multi-signal greenwashing detection mechanism to identify misleading sustainability claims. This system improves accuracy, transparency, and scalability in ESG analysis and provides evidence-based insights for better decision-making.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.5281/zenodo.19934799first seen 2026-05-05 21:29:14
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。