Climate AI for Corporate Decarbonization Metrics Extraction

TL;DR

This paper presents CAI, a novel AI pipeline using Large Language Models to automate extraction and validation of corporate GHG emission targets from disclosures, improving efficiency and accuracy in sustainability data collection.

Contribution

Introduction of CAI, a new LLM-based framework for automating the extraction and validation of corporate decarbonization metrics from textual disclosures.

Findings

Automates data curation and validation process.

Enhances efficiency and accuracy of sustainability metrics extraction.

Framework is adaptable to different LLMs.

Abstract

Corporate Greenhouse Gas (GHG) emission targets are important metrics in sustainable investing [12, 16]. To provide a comprehensive view of company emission objectives, we propose an approach to source these metrics from company public disclosures. Without automation, curating these metrics manually is a labor-intensive process that requires combing through lengthy corporate sustainability disclosures that often do not follow a standard format. Furthermore, the resulting dataset needs to be validated thoroughly by Subject Matter Experts (SMEs), further lengthening the time-to-market. We introduce the Climate Artificial Intelligence for Corporate Decarbonization Metrics Extraction (CAI) model and pipeline, a novel approach utilizing Large Language Models (LLMs) to extract and validate linked metrics from corporate disclosures. We demonstrate that the process improves data collection efficiency and accuracy by automating data curation, validation, and metric scoring from public corporate disclosures. We further show that our results are agnostic to the choice of LLMs. This framework can be applied broadly to information extraction from textual data.