Structuring Sustainability Reports for Environmental Standards with LLMs guided by Ontology

by Aida Usmanova and Ricardo Usbeck

This paper is part of the proceedings of the first ClimateNLP workshop at ACL 2024. The paper is available here.

Abstract

Following the introduction of the European Sustainability Reporting Standard (ESRS), companies will have to adapt to a new policy and provide mandatory sustainability reports. However, implementing such reports entails a challenge, such as the comprehension of a large number of textual information from various sources. This task can be accelerated by employing Large Language Models (LLMs) and ontologies to effectively model the domain knowledge. In this study, we extended an existing ontology to model ESRS Topical Standard for disclosure. The developed ontology would enable automated reasoning over the data and assist in constructing Knowledge Graphs (KGs). Moreover, the proposed ontology extension would also help to identify gaps in companies’ sustainability reports with regard to the ESRS requirements.Additionally, we extracted knowledge from corporate sustainability reports via LLMs guided with a proposed ontology and developed their KG representation.

---

Usage:

1. Installation

   git clone https://github.com/aidausmanova/esrs_kg.git

2. Environment setup

   python -m venv venv
   pip install -r requirements.txt

3. The data/ folder contains sustainability reports. In this study we used pre-processed reports from Bronzini et.al 2024

4. Create results/ folder containing processed/ and raw/ subfolders

5. Running

   Extract triples with

   src/extract_triples.py

   Generate a knowledge graph from the report with

   src/generate_kg.py

   Note: before running set up your OpenAI key in both files.

6. Once KG is generated, you can visualize it with

   src/visualize_kg.py

Citation

@inproceedings{usmanova2024structuring,
    title = "Structuring Sustainability Reports for Environmental Standards with {LLM}s guided by Ontology",
    author = "Usmanova, Aida  and
      Usbeck, Ricardo",
    editor = "Stammbach, Dominik  and
      Ni, Jingwei  and
      Schimanski, Tobias  and
      Dutia, Kalyan  and
      Singh, Alok  and
      Bingler, Julia  and
      Christiaen, Christophe  and
      Kushwaha, Neetu  and
      Muccione, Veruska  and
      A. Vaghefi, Saeid  and
      Leippold, Markus",
    booktitle = "Proceedings of the 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.climatenlp-1.13/",
    doi = "10.18653/v1/2024.climatenlp-1.13",
    pages = "168--177"
}