From November 4 to 9, 2025, we were in Suzhou, China, at the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025). Luciana Benotti and Guido Ivetta took part in the event.
On Thursday, November 6, Guido presented the paper titled: “HESEIA: a community dataset for evaluating social biases in large language models, co-designed in real school environments in Latin America,” together with Luciana B. This work, developed by the Vía Libre AI team, was authored by Guido Ivetta, Marcos J. Gómez, Sofía Martinelli, Pietro Palombini, M. Emilia Echeveste, Nair Carolina Mazzeo, Beatriz Busaniche, and Luciana Benotti. You can watch the panel below.
On November 7, Luciana Benotti took part in the session: “How will multimodal language models shape industry and society?” as part of the industry track panel. You can listen to her contribution in the session below.
For photos of the event or more information, you can read the related article.