EulerESG: Automating ESG Disclosure Analysis with LLMs
Yi Ding, Xushuo Tang, Zhengyi Yang, Wenqian Zhang, Simin Wu, Yuxin Huang, Lingjing Lan, Weiyuan Li, Yin Chen, Mingchen Ju, Wenke Yang, Thong Hoang, Mykhailo Klymenko, Xiwei Zu, Wenjie Zhang
TL;DR
EulerESG introduces an LLM-powered pipeline for extracting and aligning ESG disclosures from PDFs with SASB and other frameworks. It combines Standards-Based Metric Extraction, semantic expansion, dual-channel retrieval, and an interactive chatbot to produce structured metrics and contextual explanations. Across four global firms and 12 industry pairs, the approach achieves up to 0.95 metric-level accuracy with varying runtimes, and analyzes back-end models to balance accuracy and latency. The work enables scalable, explainable ESG analysis for regulators, investors, and corporate teams, potentially improving regulatory compliance and benchmarking.
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 \textbf{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.