# Where Should I Study? Biased Language Models Decide! Evaluating Fairness in LMs for Academic Recommendations

arXiv: https://arxiv.org/abs/2509.04498 · HTML: https://mlsanity.com/paper/2509.04498/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations](https://mlsanity.com/paper/2411.07320/) (2024)
- [Unequal Opportunities: Examining the Bias in Geographical Recommendations by Large Language Models](https://mlsanity.com/paper/2504.05325/) (2025)
- [Evaluation of Geographical Distortions in Language Models](https://mlsanity.com/paper/2404.17401/) (2024)
- [Neutralizing Bias in LLM Reasoning using Entailment Graphs](https://mlsanity.com/paper/2503.11614/) (2025)
- [Biases in Scholarly Recommender Systems: Impact, Prevalence, and Mitigation](https://mlsanity.com/paper/2301.07483/) (2023)
- [Big City Bias: Evaluating the Impact of Metropolitan Size on Computational Job Market Abilities of Language Models](https://mlsanity.com/paper/2403.08046/) (2024)

## Built on by (most cited first, 2 of 2)

- [One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization](https://mlsanity.com/paper/2601.18572/) (2026)
- [Sociodemographic Biases in Educational Counselling by Large Language Models](https://mlsanity.com/paper/2604.25932/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly used as daily recommendation systems for tasks like education planning, yet their recommendations risk perpetuating societal biases. This paper empirically examines geographic, demographic, and economic biases in university and program suggestions from three open-source LLMs: LLaMA-3.1-8B, Gemma-7B, and Mistral-7B. Using 360 simulated user profiles varying by gender, nationality, and economic status, we analyze over 25,000 recommendations. Results show strong biases: institutions in the Global North are disproportionately favored, recommendations often reinforce gender stereotypes, and institutional repetition is prevalent. While LLaMA-3.1 achieves the highest diversity, recommending 481 unique universities across 58 countries, systemic disparities persist. To quantify these issues, we propose a novel, multi-dimensional evaluation framework that goes beyond accuracy by measuring demographic and geographic representation. Our findings highlight the urgent need for bias consideration in educational LMs to ensure equitable global access to higher education.