English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Over the last decade, several regulatory bodies have started requiring thedisclosure of non-financial information from publicly listed companies, inlight of the investors' increasing attention to Environmental, Social, andGovernance (ESG) issues. Publicly released information on sustainabilitypractices is often disclosed in diverse, unstructured, and multi-modaldocumentation. This poses a challenge in efficiently gathering and aligning thedata into a unified framework to derive insights related to Corporate SocialResponsibility (CSR). Thus, using Information Extraction (IE) methods becomesan intuitive choice for delivering insightful and actionable data tostakeholders. In this study, we employ Large Language Models (LLMs), In-ContextLearning, and the Retrieval-Augmented Generation (RAG) paradigm to extractstructured insights related to ESG aspects from companies' sustainabilityreports. We then leverage graph-based representations to conduct statisticalanalyses concerning the extracted insights. These analyses revealed that ESGcriteria cover a wide range of topics, exceeding 500, often beyond thoseconsidered in existing categorizations, and are addressed by companies througha variety of initiatives. Moreover, disclosure similarities emerged amongcompanies from the same region or sector, validating ongoing hypotheses in theESG literature. Lastly, by incorporating additional company attributes into ouranalyses, we investigated which factors impact the most on companies' ESGratings, showing that ESG disclosure affects the obtained ratings more thanother financial or company data.

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