Glitter or Gold? Deriving Structured Insights from Sustainability Reports via Large Language Models

TL;DR

This paper demonstrates how Large Language Models and retrieval techniques can extract structured ESG insights from unstructured sustainability reports, revealing diverse topics, regional and sector similarities, and factors influencing ESG ratings.

Contribution

It introduces a novel application of LLMs with RAG and graph analysis to extract and analyze ESG data from sustainability reports, uncovering new insights and validation of existing hypotheses.

Findings

ESG topics exceed 500, often beyond standard categories

Companies from same region or sector show disclosure similarities

ESG disclosure significantly impacts ESG ratings

Abstract

Over the last decade, several regulatory bodies have started requiring the disclosure of non-financial information from publicly listed companies, in light of the investors' increasing attention to Environmental, Social, and Governance (ESG) issues. Publicly released information on sustainability practices is often disclosed in diverse, unstructured, and multi-modal documentation. This poses a challenge in efficiently gathering and aligning the data into a unified framework to derive insights related to Corporate Social Responsibility (CSR). Thus, using Information Extraction (IE) methods becomes an intuitive choice for delivering insightful and actionable data to stakeholders. In this study, we employ Large Language Models (LLMs), In-Context Learning, and the Retrieval-Augmented Generation (RAG) paradigm to extract structured insights related to ESG aspects from companies' sustainability reports. We then leverage graph-based representations to conduct statistical analyses concerning the extracted insights. These analyses revealed that ESG criteria cover a wide range of topics, exceeding 500, often beyond those considered in existing categorizations, and are addressed by companies through a variety of initiatives. Moreover, disclosure similarities emerged among companies from the same region or sector, validating ongoing hypotheses in the ESG literature. Lastly, by incorporating additional company attributes into our analyses, we investigated which factors impact the most on companies' ESG ratings, showing that ESG disclosure affects the obtained ratings more than other financial or company data.