The recent success of Natural Language Processing (NLP) relies heavily on pre-trained text representations such as word embeddings. However, pre-trained text representations may exhibit social biases and stereotypes, e.g., disproportionately associating gender with occupations. Though prior work presented various bias detection algorithms, they are limited to pre-defined biases and lack effective interaction support. In this work, we propose STILE, an interactive system that supports mixed-initiative bias discovery and debugging in pre-trained text representations. STILE provides users the flexibility to interactively define and customize biases to detect based on their interests. Furthermore, it provides a bird’s-eye view of detected biases in a Chord diagram and allows users to dive into the training data to investigate how a bias was developed. Our lab study and expert review confirm the usefulness and usability of STILE as an effective aid in identifying and understanding biases in pre-trained text representations.
https://doi.org/10.1145/3613904.3642111
The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)