Proceedings

PEACE 2.0: Grounded Explanations and Counter-Speech for Combating Hate Expressions

Greta Damo, Stéphane Petiot, Elena Cabrio, Serena Villata

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Demo Track. Pages 8380-8384.

https://doi.org/10.24963/ijcai.2026/961

Keywords

  • AI: AI Ethics, Trust, Fairnes
  • AI: Multidisciplinary Topics and Applications
  • AI: Natural Language Processing

Abstract

The increasing volume of hate speech on online platforms poses significant societal challenges. While the Natural Language Processing community has developed effective methods to automatically detect the presence of hate speech, responses to it, called counter-speech, are still an open challenge. We present PEACE 2.0, a novel tool that, besides analysing and explaining why a message is considered hateful or not, also generates a response to it. More specifically, PEACE 2.0 has three main new functionalities: leveraging a Retrieval-Augmented Generation (RAG) pipeline i) to ground HS explanations into evidence and facts, ii) to automatically generate evidence-grounded counter-speech, and iii) exploring the characteristics of counter-speech replies.

By integrating these capabilities, PEACE 2.0 enables in-depth analysis and response generation for both explicit and implicit hateful messages.

Greta Damo, Stéphane Petiot, Elena Cabrio, and Serena Villata. 2026. PEACE 2.0: Grounded Explanations and Counter-Speech for Combating Hate Expressions. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8380–8384. https://doi.org/10.24963/ijcai.2026/961
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards