CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools
This work addresses the lack of transparency in sustainability reporting by democratizing access to analysis tools for stakeholders, though it is incremental in improving LLM-based methods for a specific domain.
The paper tackles the problem of analyzing corporate sustainability reports, which are dense and costly for humans to process, by introducing ChatReport, an LLM-based system that automates analysis with traceable answers and expert involvement, resulting in publicly available annotated datasets and analyses for 1015 reports.
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 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.