4 papers · 1 filter
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…
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…
Teaching LLMs at Charles University: Assignments and Activities
Jindřich Helcl, Zdeněk Kasner, Ondřej Dušek +4
This paper presents teaching materials, particularly assignments and ideas for classroom activities, from a new course on large language models (LLMs) taught at Charles University.…
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…