Greench-v1: distilling SLMs on Greenwashing Detection

Federico Raspanti, Alessandro Pietro Bardelli Bardelli, Simona Scala, İrem Demirtaş, Marilena Di Bari, Michele Filannino


Abstract
Validating greenwashing claims in environmental, social, and governance (ESG) reports relies heavily on costly and inconsistent manual review. To address this, this paper introduces Greench-v1, a low-latency small language model (based on Qwen3-4B) that screens ESG text at the paragraph level. The model outputs a three-way classification (Greenwashing Alert, No Greenwashing, Not Relevant) paired with a concise, paragraph-grounded rationale to assist human auditors in triage and validation. The system was trained on a custom dataset of roughly 2,000 paragraphs, adapted from the ClimateBERT corpus. This dataset mitigates class imbalance through controlled paraphrasing of rare positive instances and uses GPT-4o to generate evidence-based justifications. Four training regimes were evaluated: (i) Hard distillation: Supervised fine-tuning on teacher-generated outputs. (ii) Soft distillation: Training the student to match the temperature-scaled logits of a domain-specialized Qwen3-14B teacher. (iii) Group Relative Policy Optimization (GRPO): Reward-based updates driven by exact-match alert generation. (iv) Hybrid GRPO: GRPO initialized from the hard-distilled checkpoint. Distillation and efficient policy optimization significantly improved performance over untuned baselines. Soft distillation and GRPO achieved the strongest results, increasing the “Greenwashing Alert” weighted F1-score by 36.7% and 49.0%, respectively, resulting in a deployable tool for screening large volumes of ESG narratives.
Anthology ID:
2026.nlp4ecology-1.8
Volume:
Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Francesca Grasso, Valerio Basile, Cristina Bosco, Muhammad Okky Ibrohim, Maria Skeppstedt, Manfred Stede
Venues:
NLP4Ecology | WS
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
79–86
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-nlp4ecology-08
DOI:
10.63317/2ngqn2gr78du
Bibkey:
Cite (ACL):
Federico Raspanti, Alessandro Pietro Bardelli Bardelli, Simona Scala, İrem Demirtaş, Marilena Di Bari, and Michele Filannino. 2026. Greench-v1: distilling SLMs on Greenwashing Detection. In Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing, pages 79–86, Palma de Mallorca, Spain. European Language Resources Association.
Cite (Informal):
Greench-v1: distilling SLMs on Greenwashing Detection (Raspanti et al., NLP4Ecology 2026)
Copy Citation: