3 papers
cs.CL2025
Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation
Tomasz Limisiewicz, David Mareček, Tomáš Musil
Mitigation of biases, such as language models' reliance on gender stereotypes, is a crucial endeavor required for the creation of reliable and useful language technology. The cruci…
cs.CL2024
Transforming Hidden States into Binary Semantic Features
Tomáš Musil, David Mareček
Large language models follow a lineage of many NLP applications that were directly inspired by distributional semantics, but do not seem to be closely related to it anymore. In thi…
cs.CL2023
Debiasing Algorithm through Model Adaptation
Tomasz Limisiewicz, David Mareček, Tomáš Musil
Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemmi…