Proud of @chiaramanna.bsky.social and Argentina Anna Rescigno who had their papers accepted at #LREC2026:
👏Manna et al.: on gender bias in decoder-only
arxiv.org/abs/2603.17952
👏Rescigno et al.: on ConGA - a framework for contextual gender annotation in MT
arxiv.org/abs/2603.17962
arxiv.org
Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only Architectures
While Large Language Models achieve state-of-the-art results across a wide range of NLP tasks, they remain prone to systematic biases. Among these, gender bias is particularly salient in MT, due to sy...
