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

2025-10-25

AI Summary

Addressing the lack of cross-entity comparability in global corporate carbon disclosure—stemming from high heterogeneity and unstructured formats—this study develops a climate disclosure quality assessment framework leveraging large language models (LLMs). Methodologically, it introduces a standardized paradigm integrating rule-based primary scoring with percentile normalization, enabling semantic parsing, quantitative scoring, and longitudinal comparability analysis of unstructured text across 11 years of CDP data. Its key contribution lies in overcoming limitations of manual coding by synergizing rule-guided evaluation with LLM-driven semantic understanding, thereby establishing a unified, cross-sectoral and cross-national metric for disclosure quality. Empirical results reveal sustained leadership in disclosure quality among technology firms and jurisdictions such as Germany, offering verifiable, scalable quantitative evidence to inform ESG investment decisions, regulatory compliance assessments, and climate strategy formulation.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Data Mining & Knowledge Management: Intelligent Query Processing
• Search and Optimization: Evaluation and Analysis

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

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.

Problem

• Assessing corporate carbon disclosure quality using large language models
• Analyzing heterogeneous climate disclosures for benchmarking and compliance
• Transforming unstructured environmental data into actionable intelligence

Innovation

• Leveraging LLMs to assess corporate climate disclosure quality
• Developing master rubric harmonizing narrative scoring across years
• Integrating rubric-guided scoring with percentile-based normalization