Measuring Harmful Representations in Scandinavian Language Models
This research addresses the problem of harmful representations in language models for Scandinavian languages, which could lead to problematic real-world outcomes, and is incremental as it applies existing methods to new data.
The study investigated gender-based harmful and toxic content in Scandinavian language models, finding that these models contain harmful stereotypes with similar values across Danish, Swedish, and Norwegian, contradicting expectations of gender equality in the region.
Scandinavian countries are perceived as role-models when it comes to gender equality. With the advent of pre-trained language models and their widespread usage, we investigate to what extent gender-based harmful and toxic content exist in selected Scandinavian language models. We examine nine models, covering Danish, Swedish, and Norwegian, by manually creating template-based sentences and probing the models for completion. We evaluate the completions using two methods for measuring harmful and toxic completions and provide a thorough analysis of the results. We show that Scandinavian pre-trained language models contain harmful and gender-based stereotypes with similar values across all languages. This finding goes against the general expectations related to gender equality in Scandinavian countries and shows the possible problematic outcomes of using such models in real-world settings.