Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.00006 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917375759089664 |
|---|---|
| author | Li, Wanxin McNeney, Denver Prabhu, Nivedita Zhang, Charlene Barr, Renee Kitching, Matthew Duc, Khanh Dao Boyce, Anthony S. |
| author_facet | Li, Wanxin McNeney, Denver Prabhu, Nivedita Zhang, Charlene Barr, Renee Kitching, Matthew Duc, Khanh Dao Boyce, Anthony S. |
| contents | AI-powered recruitment tools are increasingly adopted in personnel selection, yet they struggle to capture the requisition (req)-specific personal competencies (PCs) that distinguish successful candidates beyond job categories. We propose a large language model (LLM)-based approach to identify and prioritize req-specific PCs from reqs. Our approach integrates dynamic few-shot prompting, reflection-based self-improvement, similarity-based filtering, and multi-stage validation. Applied to a dataset of Program Manager reqs, our approach correctly identifies the highest-priority req-specific PCs with an average accuracy of 0.76, approaching human expert inter-rater reliability, and maintains a low out-of-scope rate of 0.07. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00006 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scalable Identification and Prioritization of Requisition-Specific Personal Competencies Using Large Language Models Li, Wanxin McNeney, Denver Prabhu, Nivedita Zhang, Charlene Barr, Renee Kitching, Matthew Duc, Khanh Dao Boyce, Anthony S. Computation and Language Computers and Society Information Retrieval Machine Learning AI-powered recruitment tools are increasingly adopted in personnel selection, yet they struggle to capture the requisition (req)-specific personal competencies (PCs) that distinguish successful candidates beyond job categories. We propose a large language model (LLM)-based approach to identify and prioritize req-specific PCs from reqs. Our approach integrates dynamic few-shot prompting, reflection-based self-improvement, similarity-based filtering, and multi-stage validation. Applied to a dataset of Program Manager reqs, our approach correctly identifies the highest-priority req-specific PCs with an average accuracy of 0.76, approaching human expert inter-rater reliability, and maintains a low out-of-scope rate of 0.07. |
| title | Scalable Identification and Prioritization of Requisition-Specific Personal Competencies Using Large Language Models |
| topic | Computation and Language Computers and Society Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2604.00006 |