25 citations · 106 across the 16 of their papers we have counts for
7 papers · 1 filter
A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation
Giuseppe Attanasio, Flor Miriam Plaza-del-Arco, Debora Nozza +1
Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case. However, current research often…
Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features
Eliana Pastor, Alkis Koudounas, Giuseppe Attanasio +2
Recent advances in eXplainable AI (XAI) have provided new insights into how models for vision, language, and tabular data operate. However, few approaches exist for understanding s…
Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization
Helena Bonaldi, Giuseppe Attanasio, Debora Nozza +1
Recent computational approaches for combating online hate speech involve the automatic generation of counter narratives by adapting Pretrained Transformer-based Language Models (PL…
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
Federico Bianchi, Mirac Suzgun, Giuseppe Attanasio +4
Training large language models to follow instructions makes them perform better on a wide range of tasks and generally become more helpful. However, a perfectly helpful model will…
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Paul Röttger, Hannah Rose Kirk, Bertie Vidgen +3
Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This risk motivates safety efforts such as red-teaming and l…
ITALIC: An Italian Intent Classification Dataset
Alkis Koudounas, Moreno La Quatra, Lorenzo Vaiani +5
Recent large-scale Spoken Language Understanding datasets focus predominantly on English and do not account for language-specific phenomena such as particular phonemes or words in…
E Pluribus Unum: Guidelines on Multi-Objective Evaluation of Recommender Systems
Patrick John Chia, Giuseppe Attanasio, Jacopo Tagliabue +5
Recommender Systems today are still mostly evaluated in terms of accuracy, with other aspects beyond the immediate relevance of recommendations, such as diversity, long-term user r…