Browse Teach Curate

Bias Patterns in LLM-Based Academic Paper Recommendation

An empirical study of how large language models behave when asked to recommend important papers and scholars in a research field. Students learn that LLM recommendations skew toward highly-cited, recently-published papers with larger author teams, amplifying the Matthew Effect, while, unlike documented human biases, showing no systematic gender, race, or country skew in scholar recommendations.

Data Text

Who Gets Recommended? Investigating Gender, Race, and Country Disparities in Paper Recommendations

This paper investigates the performance of several representative large models in the tasks of literature recommendation and explores potential biases in research exposure. The results indicate that …