CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools
Ni J, Bingler J, Colesanti-Senni C, Kraus M, Gostlow G, Schimanski T, Stammbach D, Vaghefi SA, Wang Q, Webersinke N, Wekhof T, Yu T, Leippold M (2023)
Publication Type: Conference contribution
Publication year: 2023
Publisher: Association for Computational Linguistics (ACL)
Pages Range: 21-51
Conference Proceedings Title: EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings of the System Demonstrations
Event location: Singapore, SGP
Abstract
In the face of climate change, are companies really taking substantial steps toward more sustainable operations? A comprehensive answer lies in the dense, information-rich landscape of corporate sustainability reports. However, the sheer volume and complexity of these reports make human analysis very costly. Therefore, only a few entities worldwide have the resources to analyze these reports at scale, which leads to a lack of transparency in sustainability reporting. Empowering stakeholders with LLM-based automatic analysis tools can be a promising way to democratize sustainability report analysis. However, developing such tools is challenging due to (1) the hallucination of LLMs and (2) the inefficiency of bringing domain experts into the AI development loop. In this paper, we introduce CHATREPORT, a novel LLM-based system to automate the analysis of corporate sustainability reports, addressing existing challenges by (1) making the answers traceable to reduce the harm of hallucination and (2) actively involving domain experts in the development loop. We make our methodology, annotated datasets, and generated analyses of 1015 reports publicly available.
Authors with CRIS profile
Involved external institutions
University of Zurich / Universität Zürich (UZH)
Switzerland (CH)
University of Oxford
United Kingdom (GB)
Eidgenössische Technische Hochschule Zürich (ETHZ) / Swiss Federal Institute of Technology in Zurich
Switzerland (CH)
Switzerland (CH)
University of Oxford
United Kingdom (GB)
Eidgenössische Technische Hochschule Zürich (ETHZ) / Swiss Federal Institute of Technology in Zurich
Switzerland (CH)
How to cite
APA:
Ni, J., Bingler, J., Colesanti-Senni, C., Kraus, M., Gostlow, G., Schimanski, T.,... Leippold, M. (2023). CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools. In Yansong Feng, Els Lefever (Eds.), EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings of the System Demonstrations (pp. 21-51). Singapore, SGP: Association for Computational Linguistics (ACL).
MLA:
Ni, Jingwei, et al. "CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools." Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, SGP Ed. Yansong Feng, Els Lefever, Association for Computational Linguistics (ACL), 2023. 21-51.
BibTeX: Download