Assessing GPT's Bias Towards Stigmatized Social Groups: An Intersectional Case Study on Nationality Prejudice and Psychophobia
Year: 2025
Type: preprint
Abstract: Recent studies have separately highlighted significant biases within foundational large language models (LLMs) against certain nationalities and stigmatized social groups. This research investigates the ethical implications of these biases intersecting with outputs of widely-used GPT-3.5/4/4o LLMS. Through structured prompt series, we evaluate model responses to several scenarios involving American and North Korean nationalities with various mental disabilities. Findings reveal significant discrepancies in empathy levels with North Koreans facing greater negative bias, particularly when mental disability is also a factor. This underscores the need for improvements in LLMs designed with a nuanced understanding of intersectional identity.
Source: arXiv (Cornell University)
Authors: Kashif, Afifah, Patel, Heer
Institution: University of Washington
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
SDG: Reduced inequalities
Open Access status: green
OpenAlex ID: W6949146532
Cites:
Cited by:
Related to: