In this task, participants must be able to generate a response to an offensive message in Spanish, which should be reasoned, respectful, non-offensive, and contain specific and truthful information. The target groups of the offensive message are: people with disabilities, Jews, LGBT+ individuals, migrants, Muslims, racialized people, women, and other groups.
Publication
Vallecillo-RodrÃguez et al. (2024). Overview of RefutES at IberLEF 2024: Automatic Generation of Counter Speech in Spanish. Procesamiento del Lenguaje Natural, Revista, 73: 449-459.
Language
Spanish
NLP topic
Dataset
Year
2024
Publication link
Ranking metric
BERTScore
Task results
| System | BERTScore Sort ascending |
|---|---|
| xa-run | 0.89 |
| Llama RefutES | 0.89 |
| LLaMA ZSL | 0.87 |
| Ixa-run2 | 0.86 |
| Ixa-run1 | 0.86 |
