17 documents
- Fanny Ducel, Aurélie Névéol, Karën Fort. "You'll be a nurse, my son!" Automatically Assessing Gender Biases in Autoregressive Language Models in French and Italian. Language Resources and Evaluation, 2024, pp.1495-1523. ⟨10.1007/s10579-024-09780-6⟩. ⟨hal-04803403⟩
- Mohammed Rameez Rameez Qureshi, Naïm Es-Sebbani, Luis Galárraga, Yvette Graham, Miguel Couceiro, et al.. REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning. ECAI 2024 - 27th European Conference on Artificial Intelligence, Oct 2024, Santiago de Compostela, Spain. pp.4027-4034, ⟨10.3233/FAIA240970⟩. ⟨hal-04872144⟩
- Ajinkya Kulkarni, Atharva Kulkarni, Isabel Trancoso, Miguel Couceiro. Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems. Interspeech 2024, Sep 2024, Kos / Greece, Greece. ⟨hal-04610235⟩
- Fanny Ducel, Aurélie Névéol, Karën Fort. Évaluation automatique des biais de genre dans des modèles de langue auto-régressifs. 31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024), Jul 2024, Toulouse, France. pp.64-84. ⟨hal-04621134⟩
- Clément Morand, Anne-Laure Ligozat, Aurélie Névéol. MLCA: a tool for Machine Learning Life Cycle Assessment. 2024 10th International Conference on ICT for Sustainability (ICT4S), Jun 2024, Stockholm, Sweden. pp.227-238, ⟨10.1109/ICT4S64576.2024.00031⟩. ⟨hal-04643414⟩
- Guilherme Dean Pelegrina, Miguel Couceiro, Leonardo Tomazeli Duarte. A preprocessing Shapley value-based approach to detect relevant and disparity prone features in machine learning. ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT 2024), Fabro Steibel, Meg Young, Ricardo Baeza-Yates, Jun 2024, Rio de Janeiro (BR), Brazil. pp.279-289, ⟨10.1145/3630106.3658905⟩. ⟨hal-04568343⟩
- Ajinkya Kulkarni, Anna Tokareva, Mohammed Rameez Qureshi, Miguel Couceiro. The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese. EACL 2024 LT-EDI WorkShop, Mar 2024, St. Julians, Malta. ⟨hal-04436147⟩
Documents récupérés de l'archive ouverte HAL 