Unveiling Gender Bias in Large Language Models: Using Teacher's Evaluation in Higher Education As an Example

TL;DR

This study reveals gender biases in GPT-4 generated teacher evaluations, showing societal stereotypes influence language use, with female instructors associated with approachability and support, and male instructors linked to entertainment.

Contribution

It introduces a comprehensive analytical framework combining OR, WEAT, sentiment, and contextual analysis to detect gender bias in LLM outputs in education.

Findings

Gender-associated language reflects societal stereotypes.

Words related to approachability/support are more used for female instructors.

Entertainment-related words are more used for male instructors.

Abstract

This paper investigates gender bias in Large Language Model (LLM)-generated teacher evaluations in higher education setting, focusing on evaluations produced by GPT-4 across six academic subjects. By applying a comprehensive analytical framework that includes Odds Ratio (OR) analysis, Word Embedding Association Test (WEAT), sentiment analysis, and contextual analysis, this paper identified patterns of gender-associated language reflecting societal stereotypes. Specifically, words related to approachability and support were used more frequently for female instructors, while words related to entertainment were predominantly used for male instructors, aligning with the concepts of communal and agentic behaviors. The study also found moderate to strong associations between male salient adjectives and male names, though career and family words did not distinctly capture gender biases. These findings align with prior research on societal norms and stereotypes, reinforcing the notion that LLM-generated text reflects existing biases.