ARTICLE
28 April 2026

基于LoRA 微调的大模型就业推荐框架

丽宏 黄1
Show Less
1 广东省外语艺术职业学院, 中国
TACS 2026 , 3(8), 171–173; https://doi.org/10.61369/TACS.2026080048
© 2026 by the Author(s). Licensee Art and Technology, USA. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC BY-NC 4.0) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

校园招聘场景下,应届生岗位精准匹配是就业推荐的核心需求,传统小模型就业推荐算法存在精度不足、语义理解缺失、交互性差等缺陷。大语言模型(LLM)强大的自然语言理解能力,为解决该问题提供了新路径。本文提出一种融合协同过滤思想与低秩适应(LoRA)微调技术的大模型就业推荐框架,将学生结构化表格数据转为自然文本,通过协同过滤筛选潜在岗位,构建动态提示词(Prompt)并结合学生特征文本作为模型输入,依托LoRA 微调实现就业岗位精准推荐。基于2021-2023年本校学生就业数据开展实验,结果表明,本文算法相较传统推荐算法及常规大模型微调推荐算法性能更优,准确率较传统算法最高提升0.2598,较通用大模型方法最高提升0.3930,可显著提升毕业生就业岗位推荐的精准度。

Keywords
LoRA 微调
大语言模型
就业推荐
协同过滤
CFR-LoRA
References

[1] 黄少成, 唐雨晴. 高校" 慢就业" 群体画像、成因及对策[J]. 思想理论教育,2024(09):107-111.
[2] 张钦彤, 王昱超, 王鹤羲, 等. 大语言模型微调技术的研究综述[J]. 计算机工程与应用,2024,60(17):17-33.
[3]Hamadi R. Large Language Models Meet Computer Vision: A Brief Survey[J]. arXiv:2311.16673v1,2023.
[4]Aghajanyan A,Gupta S,Zettlemoyer L. Intrinsic dimensionality explains the effectiveness of language model fine-tuning[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.2021:7319-7328.
[5] 曾碧卿, 陈鹏飞, 姚勇涛. 融合思维链和低秩自适应微调的方面情感三元组抽取[J]. 计算机工程,2024,50(07):53-62.
[6]Mao Y,Ge Y,Fan Y,et al. A Survey on LoRA of Large Language Models[J]. arXiv:2407.11046v4,2024.
[7]Patel R,Vishwakarma S K. An Efficient Approach for Job Recommendation System Based on Collaborative Filtering[M].Advances in Intelligent Systems and Computing,2020,1077. 
[8]Martinez-Gil J,Freudenthaler B,Natschläger T. Recommendation of job offers using random forests and support vector machines[C]//CEUR Workshop Proceedings,2018,2083:22-27.
[9]Sharma S,Rana V,Kumar V. Deep learning based semantic personalized recommendation system[J]. International Journal of Information Management Data Insights,2021,1(2):100028.
[10]Liu W,Fan H,Xia M. Credit Scoring Based on Tree-Enhanced Gradient Boosting Decision Trees[J]. Expert Syst. Appl,2022,189:116034.

Share
Back to top