ESG Classification by Implicit Rule Learning via GPT-4

arXiv:2403.15040v1 Announce Type: new
Abstract: Environmental, social, and governance (ESG) factors are widely adopted as higher investment return indicators. Accordingly, ongoing efforts are being made to automate ESG evaluation with language models to extract signals from massive web text easily. However, recent approaches suffer from a lack of training data, as rating agencies keep their evaluation metrics confidential. This paper investigates whether state-of-the-art language models like GPT-4 can be guided to align with unknown ESG evaluation criteria through strategies such …

abstract arxiv automate classification cs.cl data environmental esg evaluation extract governance gpt gpt-4 however investment language language models massive social text training training data type via web