Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

HRGraph: Leveraging LLMs for HR Data Knowledge Graphs with Information Propagation-based Job Recommendation

Azmine Toushik Wasi

TL;DR

HRGraph presents a framework that builds HR knowledge graphs from CVs and job descriptions by combining LLM-based entity extraction with BERT-derived node features to create a structured KG G=(V,E,X). The resulting HRKGs support downstream tasks such as job matching and job area classification, validated through information-propagation-based recommendations and KG-enabled GNNs on CV/JD data. Visualizations confirm rich interconnections between skills, education, and job roles, while empirical results demonstrate competitive or superior performance to baselines in both recommendation and classification tasks. The work offers a practical path toward HR analytics with open-source code, though it acknowledges challenges like LLM hallucinations and privacy concerns for future work.

Abstract

Knowledge Graphs (KGs) serving as semantic networks, prove highly effective in managing complex interconnected data in different domains, by offering a unified, contextualized, and structured representation with flexibility that allows for easy adaptation to evolving knowledge. Processing complex Human Resources (HR) data, KGs can help in different HR functions like recruitment, job matching, identifying learning gaps, and enhancing employee retention. Despite their potential, limited efforts have been made to implement practical HR knowledge graphs. This study addresses this gap by presenting a framework for effectively developing HR knowledge graphs from documents using Large Language Models. The resulting KG can be used for a variety of downstream tasks, including job matching, identifying employee skill gaps, and many more. In this work, we showcase instances where HR KGs prove instrumental in precise job matching, yielding advantages for both employers and employees. Empirical evidence from experiments with information propagation in KGs and Graph Neural Nets, along with case studies underscores the effectiveness of KGs in tasks such as job and employee recommendations and job area classification. Code and data are available at : https://github.com/azminewasi/HRGraph

HRGraph: Leveraging LLMs for HR Data Knowledge Graphs with Information Propagation-based Job Recommendation

TL;DR

HRGraph presents a framework that builds HR knowledge graphs from CVs and job descriptions by combining LLM-based entity extraction with BERT-derived node features to create a structured KG G=(V,E,X). The resulting HRKGs support downstream tasks such as job matching and job area classification, validated through information-propagation-based recommendations and KG-enabled GNNs on CV/JD data. Visualizations confirm rich interconnections between skills, education, and job roles, while empirical results demonstrate competitive or superior performance to baselines in both recommendation and classification tasks. The work offers a practical path toward HR analytics with open-source code, though it acknowledges challenges like LLM hallucinations and privacy concerns for future work.

Abstract

Knowledge Graphs (KGs) serving as semantic networks, prove highly effective in managing complex interconnected data in different domains, by offering a unified, contextualized, and structured representation with flexibility that allows for easy adaptation to evolving knowledge. Processing complex Human Resources (HR) data, KGs can help in different HR functions like recruitment, job matching, identifying learning gaps, and enhancing employee retention. Despite their potential, limited efforts have been made to implement practical HR knowledge graphs. This study addresses this gap by presenting a framework for effectively developing HR knowledge graphs from documents using Large Language Models. The resulting KG can be used for a variety of downstream tasks, including job matching, identifying employee skill gaps, and many more. In this work, we showcase instances where HR KGs prove instrumental in precise job matching, yielding advantages for both employers and employees. Empirical evidence from experiments with information propagation in KGs and Graph Neural Nets, along with case studies underscores the effectiveness of KGs in tasks such as job and employee recommendations and job area classification. Code and data are available at : https://github.com/azminewasi/HRGraph
Paper Structure (17 sections, 4 figures, 2 tables)

This paper contains 17 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Applications of Knowledge Graphs
  4. HR Data and Knowledge Graphs
  5. Methodology
  6. Experiments with Knowledge Graphs
  7. Visualizing Knowledge Graphs
  8. Downstream Tasks
  9. Information Propagation on HRGraph
  10. Task 01: Recommendation
  11. Task 02: Job Area Classification
  12. Discussion
  13. Conclusion
  14. Experimental Details
  15. Implementation Details
  16. ...and 2 more sections

Figures (4)

  • Figure 1: The overall framework of our HRGraph. It involves passing text data extracted from HR documents through a LLM to obtain entities and entity types, which are used to build a base knowledge graph with optional node features as BERT embeddings.
  • Figure 2: An overview of Job Matching and Recommendation framework using HR KGs of job applicants or employees. Using the intuition that company JDs and employee CVs or profiles should share matching entities like skills, experience, and education, we can match, find, and recommend employees from a knowledge graph. On the other hand, using a KG of many different job descriptions, we can use job-seeker skills, education, and other factors to find an appropriate employment to recommend.
  • Figure 3: Our CV Knowledge Graph. Green dots are persons (CV), blue dots are skills, education and other entities
  • Figure 4: Our Job Description Knowledge Graph. Red dots are Jobs, blue dots are skills, education and other entities