Towards Robust ESG Analysis Against Greenwashing Risks: Aspect-Action Analysis with Cross-Category Generalization

2025-02-20

AI Summary

Existing NLP methods for ESG analysis lack robustness against greenwashing—frequently misclassifying exaggerated or misleading sustainability claims as genuine performance. Method: We introduce A3CG, the first open-source benchmark explicitly designed for evaluating greenwashing robustness, featuring a novel “aspect–action” fine-grained annotation schema that explicitly links ESG dimensions (e.g., carbon emissions, diversity) to verifiable, concrete actions (e.g., “installing solar panels”). To mitigate bias from selective corporate disclosure, we propose a cross-category generalization evaluation framework. Our approach integrates supervised learning with large language models (LLMs), leveraging structured prompting and domain-specific fine-tuning for joint aspect-action extraction and generalizable modeling. Contribution/Results: Experiments reveal substantial greenwashing recognition biases in mainstream models; our method achieves a 32.7% improvement in cross-category generalization performance, establishing a new state of the art for robust ESG claim verification.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Sustainability reports are key for evaluating companies' environmental, social and governance, ESG performance, but their content is increasingly obscured by greenwashing - sustainability claims that are misleading, exaggerated, and fabricated. Yet, existing NLP approaches for ESG analysis lack robustness against greenwashing risks, often extracting insights that reflect misleading or exaggerated sustainability claims rather than objective ESG performance. To bridge this gap, we introduce A3CG - Aspect-Action Analysis with Cross-Category Generalization, as a novel dataset to improve the robustness of ESG analysis amid the prevalence of greenwashing. By explicitly linking sustainability aspects with their associated actions, A3CG facilitates a more fine-grained and transparent evaluation of sustainability claims, ensuring that insights are grounded in verifiable actions rather than vague or misleading rhetoric. Additionally, A3CG emphasizes cross-category generalization. This ensures robust model performance in aspect-action analysis even when companies change their reports to selectively favor certain sustainability areas. Through experiments on A3CG, we analyze state-of-the-art supervised models and LLMs, uncovering their limitations and outlining key directions for future research.

Problem

• Enhance ESG analysis robustness against greenwashing
• Link sustainability aspects with verifiable actions
• Ensure cross-category generalization in ESG reports

Innovation

• Aspect-Action Analysis
• Cross-Category Generalization
• Robust ESG Analysis