Skill-LLM: Repurposing General-Purpose LLMs for Skill Extraction

Amirhossein Herandi, Yitao Li, Zhanlin Liu, Ximin Hu, Xiao Cai
10/15/2024
cs.CL

No official code found. Best implementation: herandy/Skill-LLM (7 stars, last commit 2024-08-19).

Abstract

Accurate skill extraction from job descriptions is crucial in the hiring process but remains challenging. Named Entity Recognition (NER) is a common approach used to address this issue. With the demonstrated success of large language models (LLMs) in various NLP tasks, including NER, we propose fine-tuning a specialized Skill-LLM and a light weight model to improve the precision and quality of skill extraction. In our study, we evaluated the fine-tuned Skill-LLM and the light weight model using a benchmark dataset and compared its performance against state-of-the-art (SOTA) methods. Our results show that this approach outperforms existing SOTA techniques.

View on arXivView PDF

Code Implementations(1)

herandy/Skill-LLMCommunity100%
76Shell, PythonAug 19, 20242 years ago

Similar Papers

Comparative Analysis of Encoder-Based NER and Large Language Models for Skill Extraction from Russian Job Vacancies

88% match2024

NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data

86% match1 repo152024

LTNER: Large Language Model Tagging for Named Entity Recognition with Contextualized Entity Marking

86% match2024

Rethinking Skill Extraction in the Job Market Domain using Large Language Models

85% match1 repo32024

LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition

85% match2024

Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Models

84% match1 repo52025

Cite this paper

@article{herandi2024skillllm,
  title  = {Skill-LLM: Repurposing General-Purpose LLMs for Skill Extraction},
  author = {Amirhossein Herandi and Yitao Li and Zhanlin Liu and Ximin Hu and Xiao Cai},
  year   = {2024},
  eprint = {2410.12052},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.12052v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.12052.svg)](https://codeofpaper.com/paper/2410.12052)

Discussion