Where Should I Study? Biased Language Models Decide! Evaluating Fairness in LMs for Academic Recommendations
This addresses fairness issues in educational recommendation systems for global users, but it is incremental as it evaluates existing models with a new framework.
This paper tackled the problem of biases in large language models (LLMs) used for academic recommendations, finding strong geographic, demographic, and economic biases, such as favoring institutions in the Global North and reinforcing gender stereotypes, with LLaMA-3.1 recommending 481 unique universities across 58 countries but systemic disparities persisting.
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.