DIMEMEX 2025: Detection of Hate Speech, Inappropriate, and Harmless Memes Using LLMs

The objective of this task is to classify each meme into one of three mutually exclusive categories: hate speech, inappropriate content, or harmless content, using exclusively large language models (LLMs).

Publication
Jarquín-Vásquez, H. et al. 2025. Overview of DIMEMEX at IberLEF 2025: Detection of Inappropriate Memes from Mexico. Procesamiento del Lenguaje Natural, 75, pp. 401-412.
Competition
DIMEMEX: Detection of Inappropriate Memes from Mexico
Language
Spanish
URL Task
https://sites.google.com/view/dimemex-2025
NLP topic
hate detection
Dataset
DIMEMEX-2025
Year
2025
Publication link
http://journal.sepln.org/sepl…

Task results

If you have published a result better than those on the list, send a message to odesia-comunicacion@lsi.uned.es indicating the result and the DOI of the article, along with a copy of it if it is not published openly.