Finspector: A Human-Centered Visual Inspection Tool for Exploring and Comparing Biases among Foundation Models
This tool addresses bias detection for researchers and practitioners in AI, though it is incremental as it builds on existing visual analytics methods.
The researchers tackled the problem of hidden biases in pre-trained transformer-based language models by developing Finspector, a human-centered visual inspection tool that uses log-likelihood scores to detect biases, enabling easier identification and contributing to fairer model deployment.
Pre-trained transformer-based language models are becoming increasingly popular due to their exceptional performance on various benchmarks. However, concerns persist regarding the presence of hidden biases within these models, which can lead to discriminatory outcomes and reinforce harmful stereotypes. To address this issue, we propose Finspector, a human-centered visual inspection tool designed to detect biases in different categories through log-likelihood scores generated by language models. The goal of the tool is to enable researchers to easily identify potential biases using visual analytics, ultimately contributing to a fairer and more just deployment of these models in both academic and industrial settings. Finspector is available at https://github.com/IBM/finspector.