Chitchat with AI: Understand the supply chain carbon disclosure of companies worldwide through Large Language Model

TL;DR

This paper introduces a novel LLM-based framework for assessing and benchmarking corporate climate disclosures from the CDP dataset, enabling scalable, interpretable, and comparable analysis of sustainability reporting across industries and countries.

Contribution

It develops a master rubric and normalization method that harmonizes narrative scoring of disclosures, facilitating cross-sector and cross-country benchmarking over a decade.

Findings

Technology sector and Germany show higher disclosure quality.

Disclosures exhibit volatility and superficial engagement in some regions.

The approach enables actionable insights for investors and regulators.

Abstract

In the context of global sustainability mandates, corporate carbon disclosure has emerged as a critical mechanism for aligning business strategy with environmental responsibility. The Carbon Disclosure Project (CDP) hosts the world's largest longitudinal dataset of climate-related survey responses, combining structured indicators with open-ended narratives, but the heterogeneity and free-form nature of these disclosures present significant analytical challenges for benchmarking, compliance monitoring, and investment screening. This paper proposes a novel decision-support framework that leverages large language models (LLMs) to assess corporate climate disclosure quality at scale. It develops a master rubric that harmonizes narrative scoring across 11 years of CDP data (2010-2020), enabling cross-sector and cross-country benchmarking. By integrating rubric-guided scoring with percentile-based normalization, our method identifies temporal trends, strategic alignment patterns, and inconsistencies in disclosure across industries and regions. Results reveal that sectors such as technology and countries like Germany consistently demonstrate higher rubric alignment, while others exhibit volatility or superficial engagement, offering insights that inform key decision-making processes for investors, regulators, and corporate environmental, social, and governance (ESG) strategists. The proposed LLM-based approach transforms unstructured disclosures into quantifiable, interpretable, comparable, and actionable intelligence, advancing the capabilities of AI-enabled decision support systems (DSSs) in the domain of climate governance.