Virginia Tech
Procedural Justice for CS Hiring: Towards Fair and Equitable Resume Matching in AI Era
Abstract
dc:description.abstractThe tech hiring pipeline, a multistage process involving resume matching, technical and HR interviews, has increasingly integrated AI-driven solutions to enhance inclusivity, productivity, and quality in hiring. Automated resume parsers (ARPs) and applicant tracking systems (ATS) now streamline candidate selection, with over 98% of Fortune 500 companies employing these tools for initial resume matching. Resume matching is crucial as it governs all the next steps in the hiring pipeline, weeding out up to 98% of unqualified candidates. However, ARPs used in resume matching are found guilty of harboring biases against racial and gender minority candidates. Thus, current resume matching is found lacking with regards to procedural justice pillars of equality, fairness, trust and transparency. Additionally, current ARPs use keyword-based resume matching, lacking context understanding leading to incorrect judgment of candidates competencies resulting in sub-optimal resume matching. Context-aware Large Language Models (LLMs) have yielded superior performance in resume matching over traditional keyword-based approaches with considerably lower racial and gender biases against minorities when compared to human evaluations. Through our work in the resume matching stage, we try to impart procedural justice in the current hiring pipeline by opting for context-aware LLM-based resume matching along with evidence-based resume matching aiming to induce equality, fairness and transparency in the current CS workforce.
Degree
thesis:*- Name thesis:degree_name
- Doctor of Philosophy
- Level thesis:degree_level
- doctoral
- Discipline thesis:degree_discipline
- Computer Science & Applications
- Department dc:contributor.department
- Computer Science and#38; Applications
- Grantor dc:publisher
- Virginia Tech
- Year dc:date.issued
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Vaishampayan, Swanand Suhas
- Chair dc:contributor.committeechair
-
- Brown, Dwayne Christian
- Committee members dc:contributor.committeemember
-
- Yao, Danfeng
- Stevenor, Brent Anthony
- Gulzar, Muhammad Ali
- Hickman, Louis
Subjects
dc:subject × 8Rights
dc:rights- Statement dc:rights
-
- In Copyright
- Licence dc:rights.uri
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Dc Identifier Other
- vt_gsexam:46946