From November 4 to 9, 2025, the EMNLP 2025 conference will take place in Suzhou, China.
Vía Libre will be represented by its team members Guido Ivetta and Luciana Benotti. On Thursday, November 6, from 10:30 to 12:00 (local time), within EMNLP, Guido will present the paper titled “HESEIA: A Community Dataset for Evaluating Social Biases in Large Language Models, Co-Designed in Real School Environments Across Latin America.” Luciana will also join him for the Q&A session. During the conference, both Luciana and Guido will also be presenting, in person, the HESEIA poster.
This work, developed by Vía Libre’s AI team, is authored by Guido Ivetta, Marcos J. Gómez, Sofía Martinelli, Pietro Palombini, M. Emilia Echeveste, Nair Carolina Mazzeo, Beatriz Busaniche, and Luciana Benotti.
The HESEIA project originated from a teacher training program carried out by Vía Libre in 2024, which involved 370 teachers and more than 5,000 students from 189 schools across Latin America. Throughout the process, participants collaboratively built a dataset of 46,499 sentences aimed at identifying and analyzing biases and stereotypes present in artificial intelligence models. Unlike existing resources, HESEIA incorporates an intersectional and situated perspective, reflecting local contexts and the pedagogical experiences of educational communities.
