DeepGreen: Effective LLM-Driven Green-washing Monitoring System Designed for Empirical Testing -- Evidence from China

2025-04-10

AI Summary

This study addresses the challenge of detecting greenwashing among A-share listed firms in China. We propose the first LLM-driven, two-stage quantitative framework for assessing corporate green practices: an initial keyword-based screening followed by iterative, dual-layer large language model–enabled semantic parsing to generate GreenImplement—a novel, original metric quantifying genuine green implementation. Validated on financial reports (89,893 words) from 68 listed companies over three years, GreenImplement significantly and positively predicts return on assets and exhibits high concordance with China Securities Index (CSI) ESG ratings. Further analysis reveals stronger greenwashing incentives among small- and medium-sized enterprises. Integrating K-means clustering, structured financial text extraction, and violin plot visualization, our approach delivers an interpretable, reproducible, AI-augmented methodology for evaluating ESG authenticity.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Search and Optimization: Evaluation and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

This paper proposes DeepGreen, an Large Language Model Driven (LLM-Driven) system for detecting corporate green-washing behaviour. Utilizing dual-layer LLM analysis, DeepGreen preliminarily identifies potential green keywords in financial statements and then assesses their implementation degree via iterative semantic analysis of LLM. A core variable GreenImplement is derived from the ratio from the two layers' output. We extract 204 financial statements of 68 companies from A-share market over three years, comprising 89,893 words, and analyse them through DeepGreen. Our analysis, supported by violin plots and K-means clustering, reveals insights and validates the variable against the Huazheng ESG rating. It offers a novel perspective for regulatory agencies and investors, serving as a proactive monitoring tool that complements traditional methods.Empirical tests show that green implementation can significantly boost the asset return rate of companies, but there is heterogeneity in scale. Small and medium-sized companies have limited contribution to asset return via green implementation, so there is a stronger motivation for green-washing.

Problem

• Detects corporate green-washing using LLM-driven analysis
• Measures green implementation in financial statements empirically
• Evaluates impact of green practices on asset returns

Innovation

• Dual-layer LLM analysis for green-washing detection
• Iterative semantic analysis assesses implementation degree
• Derives GreenImplement variable from ratio analysis