From co-creation to technical bias detection methods: an interdisciplinary showcase from the BIAS project
TL;DR
BIAS-WEAT and BIAS-SEAT are introduced, two novel metrics designed to detect biases in word embeddings and language models for Dutch, German, Icelandic, Italian, Norwegian and Turkish.
Abstract
Societal stereotypes are often reflected in, and can be reinforced by, machine learning models and linguistic resources such as word embeddings. While various benchmarks and bias detection methods have been proposed, most focus exclusively on English. When applied to other languages, these approaches typically rely on direct translations of English resources, overlooking language- and culture-specific nuances. In this paper, we introduce BIAS-WEAT and BIAS-SEAT, two novel metrics designed to detect biases in word embeddings and language models for Dutch, German, Icelandic, Italian, Norwegian and Turkish. Drawing on real-world biases identified through co-creation workshops with native speakers in the context of a hiring situation, we translated these insights into technical evaluation metrics that are applicable to general-purpose language resources. Our interdisciplinary study demonstrates how language models embed and reproduce biases that are specific to their linguistic and geographic contexts, underscoring the need for culturally grounded approaches to bias detection.1