The Biased Samaritan: LLM biases in Perceived Kindness

TL;DR

This paper introduces a novel method to evaluate demographic biases in Large Language Models by assessing their perceived kindness towards different groups, revealing biases towards baseline demographics and tendencies to help non-baseline groups more.

Contribution

The paper presents a new quantitative approach for measuring demographic biases in LLMs, distinguishing baseline biases from general tendencies to help non-baseline groups.

Findings

Models perceive the baseline demographic as a white, middle-aged or young male.

Non-baseline demographics are generally more willing to help than the baseline.

Methodology effectively separates baseline bias from bias in helping tendencies.

Abstract

While Large Language Models (LLMs) have become ubiquitous in many fields, understanding and mitigating LLM biases is an ongoing issue. This paper provides a novel method for evaluating the demographic biases of various generative AI models. By prompting models to assess a moral patient's willingness to intervene constructively, we aim to quantitatively evaluate different LLMs' biases towards various genders, races, and ages. Our work differs from existing work by aiming to determine the baseline demographic identities for various commercial models and the relationship between the baseline and other demographics. We strive to understand if these biases are positive, neutral, or negative, and the strength of these biases. This paper can contribute to the objective assessment of bias in Large Language Models and give the user or developer the power to account for these biases in LLM output or in training future LLMs. Our analysis suggested two key findings: that models view the baseline demographic as a white middle-aged or young adult male; however, a general trend across models suggested that non-baseline demographics are more willing to help than the baseline. These methodologies allowed us to distinguish these two biases that are often tangled together.