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

Lee Cohen, Connie Hong, Jack Hsieh, Judy Hanwen Shen
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11142-11172, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-cohen25a, title = {Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic {LLM} Manipulations}, author = {Cohen, Lee and Hong, Connie and Hsieh, Jack and Shen, Judy Hanwen}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {11142--11172}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/cohen25a/cohen25a.pdf}, url = {https://proceedings.mlr.press/v267/cohen25a.html}, 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.} }
Endnote
%0 Conference Paper %T Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations %A Lee Cohen %A Connie Hong %A Jack Hsieh %A Judy Hanwen Shen %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-cohen25a %I PMLR %P 11142--11172 %U https://proceedings.mlr.press/v267/cohen25a.html %V 267 %X 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.
APA
Cohen, L., Hong, C., Hsieh, J. & Shen, J.H.. (2025). Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:11142-11172 Available from https://proceedings.mlr.press/v267/cohen25a.html.

Related Material