# Assessing GPT's Bias Towards Stigmatized Social Groups: An Intersectional Case Study on Nationality Prejudice and Psychophobia

arXiv: https://arxiv.org/abs/2505.17045 · HTML: https://mlsanity.com/paper/2505.17045/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 15 May 2025.

## Builds on (most cited first, 5 of 5)

- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020)
- [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020)
- [Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks](https://mlsanity.com/paper/2306.05550/) (2023)

## Abstract (arXiv)

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.