4 papers · 1 filter
Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach
Nicolás BenjamÃn Ocampo, Agnes Paullate Nyiranziza, Davide Ceolin
Large Language Models (LLMs) have demonstrated remarkable capabilities in tasks related to reasoning and judgment. However, assessing the quality of arguments requires a rigorous e…
Leveraging Argument Structure to Predict Content Hatefulness
Nicolás BenjamÃn Ocampo, Davide Ceolin
Information disorder is a challenging phenomenon that affects society at large. This phenomenon entails the diffusion of misleading, misinforming, and hateful content online. In di…
When Hate Meets Facts: LLMs-in-the-Loop for Check-worthiness Detection in Hate Speech
Nicolás BenjamÃn Ocampo, Tommaso Caselli, Davide Ceolin
Hateful content online is often expressed using fact-like, not necessarily correct information, especially in coordinated online harassment campaigns and extremist propaganda. Fail…
Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering
Helena Bonaldi, Greta Damo, Nicolás BenjamÃn Ocampo +3
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…