3 papers
cs.CL2024
Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization
Shahed Masoudian, Markus Frohmann, Navid Rekabsaz +1
Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-t…
cs.IR2024
The Importance of Cognitive Biases in the Recommendation Ecosystem
Markus Schedl, Oleg Lesota, Stefan Brandl +3
Cognitive biases have been studied in psychology, sociology, and behavioral economics for decades. Traditionally, they have been considered a negative human trait that leads to inf…
cs.LG2024
Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters
Shahed Masoudian, Cornelia Volaucnik, Markus Schedl +1
Bias mitigation of Language Models has been the topic of many studies with a recent focus on learning separate modules like adapters for on-demand debiasing. Besides optimizing for…