2 papers
cs.CL2024
REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning
Rameez Qureshi, Naïm Es-Sebbani, Luis Galárraga +3
With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies…
cs.CL2024
The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese
Ajinkya Kulkarni, Anna Tokareva, Rameez Qureshi +1
In the field of spoken language understanding, systems like Whisper and Multilingual Massive Speech (MMS) have shown state-of-the-art performances. This study is dedicated to a com…