Giuseppe Attanasio

Latest

• XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
• Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
• Classist Tools: Social Class Correlates with Performance in NLP
• A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation
• MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection
• ferret: a Framework for Benchmarking Explainers on Transformers
• Is It Worth the (Environmental) Cost? Limited Evidence for the Benefits of Diachronic Continuous Training
• HATE-ITA: Hate Speech Detection in Italian Social Media Text
• MilaNLP at SemEval-2022 Task 5: Using Perceiver IO for Detecting Misogynous Memes with Text and Image Modalities
• Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
• Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists