A Disability Lens towards Biases in GPT-3 Generated Open-Ended Languages

TL;DR

This paper investigates biases in GPT-3 generated text from a disability perspective, aiming to identify fairness issues and improve understanding of how language models may perpetuate biases against disabled groups.

Contribution

It introduces a novel approach to measure biases in language models specifically through the lens of disability, addressing a gap in bias detection methods.

Findings

Identified biases in GPT-3 outputs related to disability.

Highlighted the importance of considering disability in fairness assessments.

Proposed a framework for bias measurement from a disability perspective.

Abstract

Language models (LM) are becoming prevalent in many language-based application spaces globally. Although these LMs are improving our day-to-day interactions with digital products, concerns remain whether open-ended languages or text generated from these models reveal any biases toward a specific group of people, thereby risking the usability of a certain product. There is a need to identify whether these models possess bias to improve the fairness in these models. This gap motivates our ongoing work, where we measured the two aspects of bias in GPT-3 generated text through a disability lens.