The Generation Gap: Exploring Age Bias in the Value Systems of Large Language Models

TL;DR

This study investigates age-related biases in large language models' value systems, revealing a tendency towards younger demographics and challenges in mitigating this bias through prompt modifications.

Contribution

It introduces a comprehensive analysis of age bias in LLMs using World Value Survey data and evaluates the effect of age identity prompts on bias mitigation.

Findings

LLMs tend to favor younger age groups in value alignment.

Age bias varies across different value categories.

Prompting with age identity has limited success in reducing bias.

Abstract

We explore the alignment of values in Large Language Models (LLMs) with specific age groups, leveraging data from the World Value Survey across thirteen categories. Through a diverse set of prompts tailored to ensure response robustness, we find a general inclination of LLM values towards younger demographics, especially when compared to the US population. Although a general inclination can be observed, we also found that this inclination toward younger groups can be different across different value categories. Additionally, we explore the impact of incorporating age identity information in prompts and observe challenges in mitigating value discrepancies with different age cohorts. Our findings highlight the age bias in LLMs and provide insights for future work. Materials for our analysis are available at \url{ https://github.com/MichiganNLP/Age-Bias-In-LLMs}