The proliferation of hate speech in digital communication platforms poses significant challenges to online safety and social cohesion. While automated hate speech detection systems have shown promise, their black-box nature limits user trust and understanding of AI-driven content moderation decisions. This paper presents a framework that integrates explainable AI (XAI) techniques with counter-speech generation to create transparent, ethical solutions for hate speech mitigation. Our approach combines a fine-tuned HateBERT model, with a specialized Llama 3.1-8B-Instruct model for generating empathetic counter-narratives. The system employs five distinct XAI methods: Integrated Gradients, Attention Visualization, LIME, Counterfactual Analysis, and Natural Language Explanations to provide interpretable reasoning behind both detection and response generation decisions. The integration of explainability mechanisms with counter-speech generation represents a novel contribution to ethical AI systems, fostering transparency and trust in automated hate speech mitigation while maintaining high performance standards for real-world deployment.

We present a new corpus of persuasion techniques for Slavic languages. The corpus contains documents from parliamentary debates in Bulgarian and Polish, and from social media in Russian, annotated with persuasion techniques at text-span and sentence level. The techniques come from a taxonomy of 25 fine-grained persuasion techniques, grouped under six broader categories of rhetorical persuasion strategies. The corpus contains approximately 7500 text spans annotated with persuasion techniques, from 222 documents that cover hotly debated topics at both international and national level. We describe the process of corpus creation, provide related statistics, elaborate on topic and persuasion technique correlations. We provide baseline models and benchmark results for detection and classification of persuasion techniques at the text-span level and sentence level, which use classic ML-based and generative AI-based models.

We present SlavicNLP 2025 Shared Task on Detection and Classification of Persuasion Techniques in Parliamentary Debates and Social Media. The task is structured into two subtasks: (1) Detection, to determine whether a given text fragment contains persuasion techniques, and (2) Classification, to determine for a given text fragment which persuasion techniques are present therein using a taxonomy of 25 persuasion technique taxonomy. The task focuses on two text genres, namely, parliamentary debates revolving around widely discussed topics, and social media, in five languages: Bulgarian, Croatian, Polish, Russian and Slovene. This task contributes to the broader effort of detecting and understanding manipulative attempts in various contexts. There were 15 teams that registered to participate in the task, of which 9 teams submitted a total of circa 220 system responses and described their approaches in 9 system description papers.