Guardado en:
Detalles Bibliográficos
Autores principales: Kaoukis, Georgios, Koufopoulos, Ioannis Aris, Psaroudaki, Eleni, Karidi, Danae Pla, Pitoura, Evaggelia, Papastefanatos, George, Tsaparas, Panayiotis
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2512.11506
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912763986575360
author Kaoukis, Georgios
Koufopoulos, Ioannis Aris
Psaroudaki, Eleni
Karidi, Danae Pla
Pitoura, Evaggelia
Papastefanatos, George
Tsaparas, Panayiotis
author_facet Kaoukis, Georgios
Koufopoulos, Ioannis Aris
Psaroudaki, Eleni
Karidi, Danae Pla
Pitoura, Evaggelia
Papastefanatos, George
Tsaparas, Panayiotis
contents As AI and web agents become pervasive in decision-making, it is critical to design intelligent systems that not only support sustainability efforts but also guard against misinformation. Greenwashing, i.e., misleading corporate sustainability claims, poses a major challenge to environmental progress. To address this challenge, we introduce EmeraldMind, a fact-centric framework integrating a domain-specific knowledge graph with retrieval-augmented generation to automate greenwashing detection. EmeraldMind builds the EmeraldGraph from diverse corporate ESG (environmental, social, and governance) reports, surfacing verifiable evidence, often missing in generic knowledge bases, and supporting large language models in claim assessment. The framework delivers justification-centric classifications, presenting transparent, evidence-backed verdicts and abstaining responsibly when claims cannot be verified. Experiments on a new greenwashing claims dataset demonstrate that EmeraldMind achieves competitive accuracy, greater coverage, and superior explanation quality compared to generic LLMs, without the need for fine-tuning or retraining.
format Preprint
id arxiv_https___arxiv_org_abs_2512_11506
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EmeraldMind: A Knowledge Graph-Augmented Framework for Greenwashing Detection
Kaoukis, Georgios
Koufopoulos, Ioannis Aris
Psaroudaki, Eleni
Karidi, Danae Pla
Pitoura, Evaggelia
Papastefanatos, George
Tsaparas, Panayiotis
Artificial Intelligence
As AI and web agents become pervasive in decision-making, it is critical to design intelligent systems that not only support sustainability efforts but also guard against misinformation. Greenwashing, i.e., misleading corporate sustainability claims, poses a major challenge to environmental progress. To address this challenge, we introduce EmeraldMind, a fact-centric framework integrating a domain-specific knowledge graph with retrieval-augmented generation to automate greenwashing detection. EmeraldMind builds the EmeraldGraph from diverse corporate ESG (environmental, social, and governance) reports, surfacing verifiable evidence, often missing in generic knowledge bases, and supporting large language models in claim assessment. The framework delivers justification-centric classifications, presenting transparent, evidence-backed verdicts and abstaining responsibly when claims cannot be verified. Experiments on a new greenwashing claims dataset demonstrate that EmeraldMind achieves competitive accuracy, greater coverage, and superior explanation quality compared to generic LLMs, without the need for fine-tuning or retraining.
title EmeraldMind: A Knowledge Graph-Augmented Framework for Greenwashing Detection
topic Artificial Intelligence
url https://arxiv.org/abs/2512.11506