# Scalable Identification and Prioritization of Requisition-Specific Personal Competencies Using Large Language Models

arXiv: https://arxiv.org/abs/2604.00006 · HTML: https://mlsanity.com/paper/2604.00006/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 38 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SkillSpan: Hard and Soft Skill Extraction from English Job Postings](https://mlsanity.com/paper/2204.12811/) (2022)
- [Extreme Multi-Label Skill Extraction Training using Large Language Models](https://mlsanity.com/paper/2307.10778/) (2023)
- [ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain](https://mlsanity.com/paper/2305.12092/) (2023)
- [SkillGPT: a RESTful API service for skill extraction and standardization using a Large Language Model](https://mlsanity.com/paper/2304.11060/) (2023)
- [Skill-LLM: Repurposing General-Purpose LLMs for Skill Extraction](https://mlsanity.com/paper/2410.12052/) (2024)
- [Dynamic Few-Shot Learning for Knowledge Graph Question Answering](https://mlsanity.com/paper/2407.01409/) (2024)

## Abstract (arXiv)

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.