Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment

TL;DR

This paper investigates demographic biases in large language models used for AI recruitment and proposes a privacy-focused framework to mitigate gender bias, demonstrating its effectiveness through experiments.

Contribution

It introduces a novel privacy-enhancing framework to reduce gender bias in LLMs for recruitment, addressing ethical concerns in high-stake AI applications.

Findings

The framework effectively reduces gender bias in LLMs.

Data biases significantly influence model behavior.

Mitigation strategies can prevent bias reproduction.

Abstract

The use of language technologies in high-stake settings is increasing in recent years, mostly motivated by the success of Large Language Models (LLMs). However, despite the great performance of LLMs, they are are susceptible to ethical concerns, such as demographic biases, accountability, or privacy. This work seeks to analyze the capacity of Transformers-based systems to learn demographic biases present in the data, using a case study on AI-based automated recruitment. We propose a privacy-enhancing framework to reduce gender information from the learning pipeline as a way to mitigate biased behaviors in the final tools. Our experiments analyze the influence of data biases on systems built on two different LLMs, and how the proposed framework effectively prevents trained systems from reproducing the bias in the data.