@inproceedings{vaishampayan-etal-2025-human,
title = "Human and {LLM}-Based Resume Matching: An Observational Study",
author = "Vaishampayan, Swanand and
Leary, Hunter and
Alebachew, Yoseph Berhanu and
Hickman, Louis and
Stevenor, Brent and
Beck, Weston and
Brown, Chris",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.270/",
doi = "10.18653/v1/2025.findings-naacl.270",
pages = "4808--4823",
ISBN = "979-8-89176-195-7",
abstract = "Resume matching assesses the extent to which candidates qualify for jobs based on the content of resumes. This process increasingly uses natural language processing (NLP) techniques to automate parsing and rating tasks{---}saving time and effort. Large language models (LLMs) are increasingly used for this purpose{---}thus, we explore their capabilities for resume matching in an observational study. We compare zero-shot GPT-4 and human ratings for 736 resumes submitted to job openings from diverse fields using real-world evaluation criteria. We also study the effects of prompt engineering techniques on GPT-4 ratings and compare differences in GPT-4 and human ratings across racial and gender groups. Our results show: LLM scores correlate minorly with humans, suggesting they are not interchangeable; prompt engineering such as CoT improves the quality of LLM ratings; and LLM scores do not show larger group differences (i.e., bias) than humans. Our findings provide implications for LLM-based resume rating to promote more fair and NLP-based resume matching in a multicultural world."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vaishampayan-etal-2025-human">
<titleInfo>
<title>Human and LLM-Based Resume Matching: An Observational Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swanand</namePart>
<namePart type="family">Vaishampayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hunter</namePart>
<namePart type="family">Leary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoseph</namePart>
<namePart type="given">Berhanu</namePart>
<namePart type="family">Alebachew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis</namePart>
<namePart type="family">Hickman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brent</namePart>
<namePart type="family">Stevenor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weston</namePart>
<namePart type="family">Beck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Brown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Resume matching assesses the extent to which candidates qualify for jobs based on the content of resumes. This process increasingly uses natural language processing (NLP) techniques to automate parsing and rating tasks—saving time and effort. Large language models (LLMs) are increasingly used for this purpose—thus, we explore their capabilities for resume matching in an observational study. We compare zero-shot GPT-4 and human ratings for 736 resumes submitted to job openings from diverse fields using real-world evaluation criteria. We also study the effects of prompt engineering techniques on GPT-4 ratings and compare differences in GPT-4 and human ratings across racial and gender groups. Our results show: LLM scores correlate minorly with humans, suggesting they are not interchangeable; prompt engineering such as CoT improves the quality of LLM ratings; and LLM scores do not show larger group differences (i.e., bias) than humans. Our findings provide implications for LLM-based resume rating to promote more fair and NLP-based resume matching in a multicultural world.</abstract>
<identifier type="citekey">vaishampayan-etal-2025-human</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.270</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.270/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>4808</start>
<end>4823</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Human and LLM-Based Resume Matching: An Observational Study
%A Vaishampayan, Swanand
%A Leary, Hunter
%A Alebachew, Yoseph Berhanu
%A Hickman, Louis
%A Stevenor, Brent
%A Beck, Weston
%A Brown, Chris
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F vaishampayan-etal-2025-human
%X Resume matching assesses the extent to which candidates qualify for jobs based on the content of resumes. This process increasingly uses natural language processing (NLP) techniques to automate parsing and rating tasks—saving time and effort. Large language models (LLMs) are increasingly used for this purpose—thus, we explore their capabilities for resume matching in an observational study. We compare zero-shot GPT-4 and human ratings for 736 resumes submitted to job openings from diverse fields using real-world evaluation criteria. We also study the effects of prompt engineering techniques on GPT-4 ratings and compare differences in GPT-4 and human ratings across racial and gender groups. Our results show: LLM scores correlate minorly with humans, suggesting they are not interchangeable; prompt engineering such as CoT improves the quality of LLM ratings; and LLM scores do not show larger group differences (i.e., bias) than humans. Our findings provide implications for LLM-based resume rating to promote more fair and NLP-based resume matching in a multicultural world.
%R 10.18653/v1/2025.findings-naacl.270
%U https://aclanthology.org/2025.findings-naacl.270/
%U https://doi.org/10.18653/v1/2025.findings-naacl.270
%P 4808-4823
Markdown (Informal)
[Human and LLM-Based Resume Matching: An Observational Study](https://aclanthology.org/2025.findings-naacl.270/) (Vaishampayan et al., Findings 2025)
ACL
- Swanand Vaishampayan, Hunter Leary, Yoseph Berhanu Alebachew, Louis Hickman, Brent Stevenor, Weston Beck, and Chris Brown. 2025. Human and LLM-Based Resume Matching: An Observational Study. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 4808–4823, Albuquerque, New Mexico. Association for Computational Linguistics.