Colombian Waitresses y Jueces canadienses: Gender and Country Biases in Occupation Recommendations from LLMs

TL;DR

This study investigates multilingual intersectional biases in occupation recommendations from large language models, revealing persistent gender and country stereotypes across languages and the influence of prompting language.

Contribution

First to analyze intersectional country and gender biases in multilingual LLM occupation recommendations, highlighting the impact of language and model tuning on bias levels.

Findings

LLMs encode significant gender and country biases.

Intersectional biases persist even when individual biases are mitigated.

Prompting language significantly influences bias levels.

Abstract

One of the goals of fairness research in NLP is to measure and mitigate stereotypical biases that are propagated by NLP systems. However, such work tends to focus on single axes of bias (most often gender) and the English language. Addressing these limitations, we contribute the first study of multilingual intersecting country and gender biases, with a focus on occupation recommendations generated by large language models. We construct a benchmark of prompts in English, Spanish and German, where we systematically vary country and gender, using 25 countries and four pronoun sets. Then, we evaluate a suite of 5 Llama-based models on this benchmark, finding that LLMs encode significant gender and country biases. Notably, we find that even when models show parity for gender or country individually, intersectional occupational biases based on both country and gender persist. We also show that the prompting language significantly affects bias, and instruction-tuned models consistently demonstrate the lowest and most stable levels of bias. Our findings highlight the need for fairness researchers to use intersectional and multilingual lenses in their work.