Enhancing Retrieval for ESGLLM via ESG-CID -- A Disclosure Content Index Finetuning Dataset for Mapping GRI and ESRS
This work solves the problem of data scarcity for ESG report automation, benefiting organizations and regulators, but it is incremental as it builds on existing RAG and embedding methods with a new dataset.
The paper tackles the challenge of automating ESG report generation by addressing the lack of labeled data for training retrieval models in RAG systems, creating the ESG-CID dataset from disclosure content indexes and showing that fine-tuned BERT-based models outperform commercial embeddings and public models, with improvements demonstrated under cross-report style transfer from GRI to ESRS.
Climate change has intensified the need for transparency and accountability in organizational practices, making Environmental, Social, and Governance (ESG) reporting increasingly crucial. Frameworks like the Global Reporting Initiative (GRI) and the new European Sustainability Reporting Standards (ESRS) aim to standardize ESG reporting, yet generating comprehensive reports remains challenging due to the considerable length of ESG documents and variability in company reporting styles. To facilitate ESG report automation, Retrieval-Augmented Generation (RAG) systems can be employed, but their development is hindered by a lack of labeled data suitable for training retrieval models. In this paper, we leverage an underutilized source of weak supervision -- the disclosure content index found in past ESG reports -- to create a comprehensive dataset, ESG-CID, for both GRI and ESRS standards. By extracting mappings between specific disclosure requirements and corresponding report sections, and refining them using a Large Language Model as a judge, we generate a robust training and evaluation set. We benchmark popular embedding models on this dataset and show that fine-tuning BERT-based models can outperform commercial embeddings and leading public models, even under temporal data splits for cross-report style transfer from GRI to ESRS. Data: https://huggingface.co/datasets/airefinery/esg_cid_retrieval