2025
HESEIA: A community-based dataset for evaluating social biases in large language models, co-designed in real school settings in Latin America
Guido Ivetta, Marcos J Gomez, Sof{\'i}a Martinelli, Pietro Palombini, M Emilia Echeveste, Nair Carolina Mazzeo +2
EMNLP 2025
Most resources for evaluating social biases in Large Language Models are developed without co-design from the communities affected by these biases, and rarely involve participatory approaches. We introduce HESEIA, a dataset of 46,499 sentences created in a professional development course. The course