Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations

TL;DR

This paper introduces a novel 'two-ticket' scheme for fair and accurate hiring using LLMs, addressing manipulation and access disparities through theoretical guarantees and empirical validation.

Contribution

It proposes a new multi-ticket framework for fair hiring under LLM manipulation, with proven guarantees and empirical validation on real resumes.

Findings

Improves fairness and accuracy in hiring decisions.

Converges to group-independent outcomes, reducing disparities.

Validated effectiveness on real resume data.

Abstract

In an era of increasingly capable foundation models, job seekers are turning to generative AI tools to enhance their application materials. However, unequal access to and knowledge about generative AI tools can harm both employers and candidates by reducing the accuracy of hiring decisions and giving some candidates an unfair advantage. To address these challenges, we introduce a new variant of the strategic classification framework tailored to manipulations performed using large language models, accommodating varying levels of manipulations and stochastic outcomes. We propose a ``two-ticket'' scheme, where the hiring algorithm applies an additional manipulation to each submitted resume and considers this manipulated version together with the original submitted resume. We establish theoretical guarantees for this scheme, showing improvements for both the fairness and accuracy of hiring decisions when the true positive rate is maximized subject to a no false positives constraint. We further generalize this approach to an $n$-ticket scheme and prove that hiring outcomes converge to a fixed, group-independent decision, eliminating disparities arising from differential LLM access. Finally, we empirically validate our framework and the performance of our two-ticket scheme on real resumes using an open-source resume screening tool.