Finspector: A Human-Centered Visual Inspection Tool for Exploring and Comparing Biases among Foundation Models

This video demonstrates how Finspector can be used to inspect biases of large language models (LLMs) like BERT, RoBERTa, and ALBERT. Finspector is a visual analytics system that consists of multiple interactive visualizations. Finspector is available as a Python package that can be launched in an interactive computing environment like Jupyter Notebook.

Abstract

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.

Publication
The 61st Annual Meeting of the Association for Computational Linguistics (ACL): System Demonstrations
Date