Shared task

Detecting greenwashing signals through a comparison of ESG reports and public media

An exploration using LLMs, embeddings and sentiment analysis

Greenwashing has remained a top concern for companies over the past two years. It happens when companies over-report positive sustainability efforts while downplaying negative impacts. This creates an information asymmetry that can mislead even highly experienced investors and other stakeholders. In this task, we create a balanced view which encompasses both self-reported and third-party, external data about the considered companies. We encourage participants to use cutting-edge NLP methods to detect indicators of greenwashing and provide more objective assessments of the considered companies. 

We recommend the following five stages: 

Please download the detailed description here. Please contact us for any related questions!

Let us know that you are participating by filling in the RSVP form below.