Towards Composable Bias Rating of AI Services

TL;DR

This paper introduces a novel, independent bias rating system for AI services that assesses bias levels, including composite services, using a two-step approach with customizable data distributions, demonstrated on text translation.

Contribution

It proposes a new 2-step bias rating method for AI services, including composite ones, independent of API providers, with customizable data distributions for more accurate bias detection.

Findings

Effective bias detection in text translation AI services.

The rating approach works on composite AI service pipelines.

Interesting bias assessment results demonstrate the method's potential.

Abstract

A new wave of decision-support systems are being built today using AI services that draw insights from data (like text and video) and incorporate them in human-in-the-loop assistance. However, just as we expect humans to be ethical, the same expectation needs to be met by automated systems that increasingly get delegated to act on their behalf. A very important aspect of an ethical behavior is to avoid (intended, perceived, or accidental) bias. Bias occurs when the data distribution is not representative enough of the natural phenomenon one wants to model and reason about. The possibly biased behavior of a service is hard to detect and handle if the AI service is merely being used and not developed from scratch, since the training data set is not available. In this situation, we envisage a 3rd party rating agency that is independent of the API producer or consumer and has its own set of biased and unbiased data, with customizable distributions. We propose a 2-step rating approach that generates bias ratings signifying whether the AI service is unbiased compensating, data-sensitive biased, or biased. The approach also works on composite services. We implement it in the context of text translation and report interesting results.