用合成数据微调LLM，提升招聘自动化匹配精度
Augmented Fine-Tuned LLMs for Enhanced Recruitment Automation
- 构建标准化JSON格式合成数据集，增强模型对招聘任务的适配性
- 微调Phi-4模型在招聘任务中达90.62%的F1分数，显著优于基线模型
- 适合关注智能招聘系统优化的研究者与企业人力资源技术团队
本文提出一种新型招聘自动化方法。通过为招聘任务专门微调大型语言模型（LLMs），提升准确率与效率。基于此前提出的多层大语言模型驱动的机器人流程自动化申请人跟踪（MLAR）系统，本研究引入新方法：构建标准化JSON格式的合成数据集以确保一致性与可扩展性。同时，利用高参数量的DeepSeek模型解析真实简历，统一转化为相同结构化格式并加入训练集，提升数据多样性与真实性。实验表明，该框架在精确匹配、F1分数、BLEU、ROUGE及整体相似度等指标上均显著优于基础模型及其他先进模型。其中，微调后的Phi-4模型取得90.62%的最高F1分数，展现出卓越的精确率与召回率。研究验证了微调LLM在招聘流程中的巨大潜力，有望革新候选人与岗位的精准匹配。
原文摘要 · Abstract (English)
This paper presents a novel approach to recruitment automation. Large Language Models (LLMs) were fine-tuned to improve accuracy and efficiency. Building upon our previous work on the Multilayer Large Language Model-Based Robotic Process Automation Applicant Tracking (MLAR) system . This work introduces a novel methodology. Training fine-tuned LLMs specifically tuned for recruitment tasks. The proposed framework addresses the limitations of generic LLMs by creating a synthetic dataset that uses a standardized JSON format. This helps ensure consistency and scalability. In addition to the synthetic data set, the resumes were parsed using DeepSeek, a high-parameter LLM. The resumes were parsed into the same structured JSON format and placed in the training set. This will help improve data diversity and realism. Through experimentation, we demonstrate significant improvements in performance metrics, such as exact match, F1 score, BLEU score, ROUGE score, and overall similarity compared to base models and other state-of-the-art LLMs. In particular, the fine-tuned Phi-4 model achieved the highest F1 score of 90.62%, indicating exceptional precision and recall in recruitment tasks. This study highlights the potential of fine-tuned LLMs. Furthermore, it will revolutionize recruitment workflows by providing more accurate candidate-job matching.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。