activity
20162026
most citedAnalyzing Item Popularity Bias of Music Recommender Systems: Are Different Genders Equally Affected?

68 citations · 359 across the 29 of their papers we have counts for

collaborators
Showing 2024Show all

2 papers · 1 filter

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.CL2024

What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition

Carolin Holtermann, Markus Frohmann, Navid Rekabsaz +1

The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks. Much research in NLP has focused on efficient methods for storing an…