Probing Social Bias in Labor Market Text Generation by ChatGPT : A Masked Language Model Approach

Ding, Lei and Hu, Yang and Denier, Nicole and Shi, Enze and Zhang, Junxi and Hu, Qirui and Hughes, Karen D. and Kong, Linglong and Jiang, Bei (2024) Probing Social Bias in Labor Market Text Generation by ChatGPT : A Masked Language Model Approach. Advances in Neural Information Processing Systems. ISSN 1049-5258 (In Press)

[thumbnail of Probing social bias in labor market text generation by ChatGPT_A masked language model approach_PAPER]
Text (Probing social bias in labor market text generation by ChatGPT_A masked language model approach_PAPER)
Probing_social_bias_in_labor_market_text_generation_by_ChatGPT_A_masked_language_model_approach_PAPER.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (1MB)
[thumbnail of Probing social bias in labor market text generation by ChatGPT_A masked language model approach_POSTER]
Text (Probing social bias in labor market text generation by ChatGPT_A masked language model approach_POSTER)
Probing_social_bias_in_labor_market_text_generation_by_ChatGPT_A_masked_language_model_approach_POSTER.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (1MB)

Abstract

As generative large language models (LLMs) such as ChatGPT gain widespread adoption in various domains, their potential to propagate and amplify social biases, particularly in high-stakes areas such as the labor market, has become a pressing concern. AI algorithms are not only widely used in the selection of job applicants, individual job seekers may also make use of generative LLMs to help develop their job application materials. Against this backdrop, this research builds on a novel experimental design to examine social biases within ChatGPT-generated job applications in response to real job advertisements. By simulating the process of job application creation, we examine the language patterns and biases that emerge when the model is prompted with diverse job postings. Notably, we present a novel bias evaluation framework based on Masked Language Models to quantitatively assess social bias based on validated inventories of social cues/words, enabling a systematic analysis of the language used. Our findings show that the increasing adoption of generative AI, not only by employers but also increasingly by individual job seekers, can reinforce and exacerbate gender and social inequalities in the labor market through the use of biased and gendered language.

Item Type:
Journal Article
Journal or Publication Title:
Advances in Neural Information Processing Systems
Uncontrolled Keywords:
Research Output Funding/yes_externally_funded
Subjects:
?? yes - externally fundedyes ??
ID Code:
225349
Deposited By:
Deposited On:
30 Oct 2024 09:35
Refereed?:
Yes
Published?:
In Press
Last Modified:
05 Dec 2024 01:01