<?xml version="1.1" encoding="utf-8"?>
<article xsi:noNamespaceSchemaLocation="http://jats.nlm.nih.gov/publishing/1.1/xsd/JATS-journalpublishing1-mathml3.xsd" dtd-version="1.1" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><front><journal-meta><journal-id journal-id-type="publisher-id">TACS</journal-id><journal-title-group><journal-title>Technology and Application of Computer Science</journal-title></journal-title-group><issn>2998-8926</issn><eissn>2998-8934</eissn><publisher><publisher-name>Art and Technology</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.61369/TACS.2026080048</article-id><article-categories><subj-group subj-group-type="heading"><subject>Article</subject></subj-group></article-categories><title>基于LoRA 微调的大模型就业推荐框架</title><url>https://artdesignp.com/journal/TACS/3/8/10.61369/TACS.2026080048</url><author>黄丽宏</author><pub-date pub-type="publication-year"><year>2026</year></pub-date><volume>3</volume><issue>8</issue><history><date date-type="pub"><published-time>2026-04-28</published-time></date></history><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。</abstract><keywords>LoRA 微调,大语言模型,就业推荐,协同过滤,CFR-LoRA</keywords></article-meta></front><body/><back><ref-list><ref id="B1" content-type="article"><label>1</label><element-citation publication-type="journal"><p>[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.&amp;nbsp;[8]Martinez-Gil J,Freudenthaler B,Natschl&amp;auml;ger 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.</p><pub-id pub-id-type="doi"/></element-citation></ref></ref-list></back></article>
