MultiPRIDE at EVALITA 2026: Overview of the Multilingual Automatic Detection of Slur Reclamation in the LGBTQ+ Context Task

Chiara Ferrando, Lia Draetta, Marco Madeddu, Mae Sosto, Viviana Patti, Paolo Rosso, Cristina Bosco, Jacinto Mata, Estrella Gualda

Keywords: Hate Speech, Slur Reclamation, LGBTQ+, Social Media, Multilingual

TL;DR: We present the overview of the MultiPRIDE, a multilingual task at EVALITA 2026, which challenged 19 participating teams to create systems for detection of slur reclamation in LGBTQ+ contexts.

Abstract:

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 reappropriated 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 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.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 2