EulerESG: Automating ESG Disclosure Analysis with LLMs

2025-11-18

AI Summary

ESG reports are predominantly published as unstructured, format-heterogeneous PDFs, impeding standardized information extraction and cross-report alignment. To address this, we propose the first method that explicitly incorporates disclosure frameworks—such as the Sustainability Accounting Standards Board (SASB)—into large language model (LLM)-based analysis via a dual-channel retrieval-augmented system: one channel performs semantic retrieval using a vector database, while the other leverages natural language inference for precise standard clause alignment. Our system supports automated metric population, cross-firm benchmarking, and interactive exploration. Integrated end-to-end, it combines information extraction, interactive visualization dashboards, and conversational querying. Evaluated on ESG reports from four global corporations across 12 SASB sub-industries, it achieves a 0.95 average accuracy. The implementation—including source code and an interactive demo—is publicly released.

Technology Category

• Natural Language Processing: Information Extraction
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Environmental, Social, and Governance (ESG) reports have become central to how companies communicate climate risk, social impact, and governance practices, yet they are still published primarily as long, heterogeneous PDF documents. This makes it difficult to systematically answer seemingly simple questions. Existing tools either rely on brittle rule-based extraction or treat ESG reports as generic text, without explicitly modelling the underlying reporting standards. We present extbf{EulerESG}, an LLM-powered system for automating ESG disclosure analysis with explicit awareness of ESG frameworks. EulerESG combines (i) dual-channel retrieval and LLM-driven disclosure analysis over ESG reports, and (ii) an interactive dashboard and chatbot for exploration, benchmarking, and explanation. Using four globally recognised companies and twelve SASB sub-industries, we show that EulerESG can automatically populate standard-aligned metric tables with high fidelity (up to 0.95 average accuracy) while remaining practical in end-to-end runtime, and we compare several recent LLM models in this setting. The full implementation, together with a demonstration video, is publicly available at https://github.com/UNSW-database/EulerESG.

Problem

• Automates analysis of lengthy ESG reports using LLMs with framework awareness
• Addresses limitations of rule-based extraction and generic text processing methods
• Enables systematic disclosure analysis through retrieval and interactive exploration tools

Innovation

• LLM-powered system for ESG disclosure analysis
• Dual-channel retrieval and LLM-driven analysis
• Interactive dashboard and chatbot for exploration