Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification

TL;DR

This paper investigates the potential of Large Language Models, especially GPT-4, to produce fair classification outcomes using a novel fairness framework and in-context learning, highlighting their advantages over other models.

Contribution

It introduces a framework for fairness regulation in LLMs, integrating fairness definitions with in-context learning and demonstration selection, pioneering fairness-focused LLM applications.

Findings

GPT-4 achieves higher fairness and accuracy than other models

The proposed framework effectively aligns LLM outputs with fairness criteria

In-context learning with fairness rules improves classification fairness

Abstract

Employing Large Language Models (LLM) in various downstream applications such as classification is crucial, especially for smaller companies lacking the expertise and resources required for fine-tuning a model. Fairness in LLMs helps ensure inclusivity, equal representation based on factors such as race, gender and promotes responsible AI deployment. As the use of LLMs has become increasingly prevalent, it is essential to assess whether LLMs can generate fair outcomes when subjected to considerations of fairness. In this study, we introduce a framework outlining fairness regulations aligned with various fairness definitions, with each definition being modulated by varying degrees of abstraction. We explore the configuration for in-context learning and the procedure for selecting in-context demonstrations using RAG, while incorporating fairness rules into the process. Experiments conducted with different LLMs indicate that GPT-4 delivers superior results in terms of both accuracy and fairness compared to other models. This work is one of the early attempts to achieve fairness in prediction tasks by utilizing LLMs through in-context learning.