# Dissecting Bias of ChatGPT in College Major Recommendations

arXiv: https://arxiv.org/abs/2401.11699 · HTML: https://mlsanity.com/paper/2401.11699/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 17 references that are in the map.
- First posted on arXiv 18 Dec 2023.

## Builds on (most cited first, 2 of 2)

- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [Bias Disparity in Recommendation Systems](https://mlsanity.com/paper/1811.01461/) (2018)

## Built on by (most cited first, 3 of 3)

- [From Superficial Outputs to Superficial Learning: Risks of Large Language Models in Education](https://mlsanity.com/paper/2509.21972/) (2025)
- [Assessing Agentic Large Language Models in Multilingual National Bias](https://mlsanity.com/paper/2502.17945/) (2025)
- [Generative AI in Heritage Practice: Improving the Accessibility of Heritage Guidance](https://mlsanity.com/paper/2510.13811/) (2025)

## Abstract (arXiv)

I investigate bias in terms of ChatGPT's college major recommendations for students with various profiles, looking at demographic disparities in factors such as race, gender, and socioeconomic status, as well as educational disparities such as score percentiles. By constructing prompts for the ChatGPT API, allowing the model to recommend majors based on high school student profiles, I evaluate bias using various metrics, including the Jaccard Coefficient, Wasserstein Metric, and STEM Disparity Score. The results of this study reveal a significant disparity in the set of recommended college majors, irrespective of the bias metric applied.