MultiPRIDE at EVALITA 2026: Overview of the multilingual detection of slur reclamation in the LGBTQ+ context task

MultiPRIDE is a shared task proposed at EVALITA 2026. The main focus of the task is the detection of slur reclamation, a linguistic phenomenon in which derogatory terms are reclaimed by members of a community. The challenge is divided in two main tasks: (A) binary detection of reclamation in social media posts and (B) contextual detection of reclamation considering users’ biographies provided within the texts. As we propose a multilingual corpus, each task is further divided into language-specific subtasks (Italian, Spanish and, English). The task has been one of the most participated at EVALITA 2026 [1] with 19 teams submitting a total of 61 runs for Task A and 27 runs for Task B. In this paper, we present the dataset, the evaluation, the participating systems, and a discussion of the results. All the code is available at https://github.com/multipride-evalita/MultiPRIDE-Task