Large language models (LLMs) trained on internet-scale corpora can exhibit systematic biases that increase the probability of unwanted behavior. In this study, we examined potential biases towards syn...
During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation efforts focus on reducing bias in generated outputs, ty...
Many works in the literature show that LLM outputs exhibit discriminatory behaviour, triggering stereotype-based inferences based on the dialect in which the inputs are written. This bias has been sho...