- 2024REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement LearningQureshi, R., Es-Sebbani, N., Galárraga, L., Graham, Y., Couceiro, M., & Bouraoui, Z.European Conference on Artificial Intelligence (ECAI) 2024
- 2024The Balancing Act: Unmasking and Alleviating ASR Biases in PortugueseKulkarni, A., Tokareva, A., Qureshi, R., & Couceiro, M.Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion @ EACL 2024
- 2024Findings of the First Workshop on Simulating Conversational Intelligence in ChatGraham, Y., Qureshi, R., Khalid, H., Lampouras, G., Iacobacci, I., & Liu, Q.Proceedings of the 1st Workshop on Simulating Conversational Intelligence in Chat (SCI-CHAT 2024) @ EACL 2024
- 2023A Reinforcement Learning Approach to Mitigating Stereotypical Biases in Language ModelsQureshi, R., Galárraga, L., & Couceiro, M.HAL Preprint ⟨hal-04426115⟩
- 2021Mitigating Unintended Bias in Masked Language ModelsQureshi, R.Computer Science [cs], HAL ⟨hal-03363353⟩
- 2019A Simple Approach to Classify Fictional and Non-Fictional GenresQureshi, R., Ranjan, S., Rajkumar, R., & Shah, K.Proceedings of the 1st Workshop on Storytelling @ ACL 2019