Social media platforms face a growing challenge in addressing abusive content and hate speech, particularly as traditional natural language processing methods often struggle with detecting nuanced and implicit instances. To tackle this issue, our study enhances Large Language Models (LLMs) in the detection and explanation of implicit hate speech, outperforming classical approaches. We focus on two key objectives: (1) determining whether jointly predicting and generating explanations for why a message is hateful improves LLMs’ accuracy, especially for implicit cases, and (2) evaluating whether incorporating information from BERT-based models can further boost detection and explanation performance. Our method evaluates and enhances LLMs’ ability to detect hate speech and explain their predictions. By combining binary classification (Hate Speech vs. Non-Hate Speech) with natural language explanations, our approach provides clearer insights into why a message is considered hateful, advancing the accuracy and interpretability of hate speech detection.

The increasing presence of hate speech (HS) on social media poses significant societal challenges. While efforts in the Natural Language Processing community have focused on automating the detection of explicit forms of HS, subtler and indirect expressions often go unnoticed. This demo presents PEACE, a novel tool that, besides detecting if a social media message contains explicit or implicit HS, also generates detailed natural language explanations for such predictions. More specifically, PEACE addresses three main challenging tasks: i) exploring the characteristics of HS messages, ii) predicting hatefulness, and iii) elucidating the reasoning behind system predictions. A REST API is also provided to exploit the tool’s functionalities.

The potential effectiveness of counterspeech as a hate speech mitigation strategy is attracting increasing interest in the NLG research community, particularly towards the task of automatically producing it.However, automatically generated responses often lack the argumentative richness which characterises expert-produced counterspeech.In this work, we focus on two aspects of counterspeech generation to produce more cogent responses.First, by investigating the tension between helpfulness and harmlessness of LLMs, we test whether the presence of safety guardrails hinders the quality of the generations.Secondly, we assess whether attacking a specific component of the hate speech results in a more effective argumentative strategy to fight online hate.By conducting an extensive human and automatic evaluation, we show how the presence of safety guardrails can be detrimental also to a task that inherently aims at fostering positive social interactions.Moreover, our results show that attacking a specific component of the hate speech, and in particular its implicit negative stereotype and its hateful parts, leads to higher-quality generations.Content warning: this paper contains unobfuscated examples some readers may find offensive