[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-258680-105":53,"doc-detail-258680-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","generative-job-recommendations-with-large-language-model-girl","Generative Job Recommendations with Large Language Model - GIRL","","Rapid growth of online recruitment has driven demand for recommender systems that streamline job search for candidates. Existing approaches largely rely on collaborative filtering or person–job matching, often functioning as black-box models and offering limited explainable guidance. They also remain retrieval-and-ranking systems over existing listings, which restricts their value as a comprehensive career AI advisor and cannot fully bridge the semantic gap between CVs and job descriptions. This work introduces GIRL, a large-language-model-based generative job recommendation framework.",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":16,"@type":70,"position":76},"https://docshare.wps.com/template/resumes/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/generative-job-recommendations-with-large-language-model-girl/258680/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/generative-job-recommendations-with-large-language-model-girl/258680.png","ImageObject",442,249,{"name":88,"@type":89},"Putri","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-22","2026-09-13",true,{"@type":98,"interactionType":99,"userInteractionCount":47},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"Why do current job recommendation methods fall short for job seekers?","Question",{"text":108,"@type":109},"They are commonly black-box matching models that provide limited explainability, and they focus on retrieving and ranking existing jobs rather than generating personalized guidance. This also leaves a semantic gap between CVs and job descriptions.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"What is GIRL and how does it recommend jobs?",{"text":113,"@type":109},"GIRL is a generative job recommendation paradigm built on large language models. It generates job descriptions tailored to a job seeker using the seeker’s CV, instead of requiring a candidate job set.",{"name":115,"@type":106,"acceptedAnswer":116},"How is GIRL trained to align with employer preferences?",{"text":117,"@type":109},"The method uses supervised fine-tuning to condition the generator on CV-to-JD creation, then trains a reward model for CV–JD matching and applies PPO-based reinforcement learning to optimize the generator using recruiter-aligned feedback.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},258680,1790443523,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":15,"category_name":16,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":47,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":135,"language":136,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":137,"faqs":138,"seo_title":139,"seo_description":61,"update_tm":140,"read_time":79},962085571259,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","Generative Job Recommendations with Large  \nLanguage Model  \nZhi Zheng 1 ,2 ,†, Zhaopeng Qiu 1 ,†, Xiao Hu 1 , Likang Wu 1 ,2 , Hengshu Zhu 1∗, Hui Xiong3 ,4∗  \n1 Career Science Lab, BOSS Zhipin.  \n2 University of Science and Technology of China,  \n3 The Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology.  \n4 The Department of Computer Science and Engineering, The Hong Kong University of Science and Technology.  \n[zhengzhi97@mail.ustc.edu.cn](zhengzhi97@mail.ustc.edu.cn), [zhpengqiu@gmail.com](zhpengqiu@gmail.com), [zhuhengshu@gmail.com](zhuhengshu@gmail.com), [xionghui@ust.hk](xionghui@ust.hk)  \narXiv :2307 .02 157v 1 [ cs .IR] 5 Jul 2023  \nAbstract—The rapid development of online recruitment services has encouraged the utilization of recommender systems to streamline the job seeking process. Predominantly, current job recommendations deploy either collaborative filtering or person-job matching strategies. However, these models tend to operate as “black-box” systems and lack the capacity to offer explainable guidance to job seekers. Moreover, conventional matching-based recommendation methods are limited to retrieving and ranking existing jobs in the database, restricting their potential as comprehensive career AI advisors. To this end, here we present GIRL (GeneratIve job Recommendation based on Large language models), a novel approach inspired by recent advancements in the field of Large Language Models (LLMs). We initially employ a Supervised Fine-Tuning (SFT) strategy to instruct the LLM-based generator in crafting suitable Job Descriptions (JDs) based on the Curriculum Vitae (CV) of a job seeker. Moreover, we propose to train a model which can evaluate the matching degree between CVs and JDs as a reward model, and we use Proximal Policy Optimization (PPO)-based Reinforcement Learning (RL) method to further fine-tine the generator. This aligns the generator with recruiter feedback, tailoring the output to better meet employer preferences. In particular, GIRL serves as a job seeker-centric generative model, providing job suggestions without the need of a candidate set. This capability also enhances the performance of existing job recommendation models by supplementing job seeking features with generated content. With extensive experiments on a large-scale real-world dataset, we demonstrate the substantial effectiveness of our approach. We believe that GIRL introduces a paradigmshifting approach to job recommendation systems, fostering amore personalized and comprehensive job-seeking experience.  \nI. INTRODUCTION  \nRecent years have witnessed the rapid development of online recruitment. According to the report from The Insight Partners 1 , the global online recruitment market size is expected to grow from $29.29 billion in 2021 to $47.31 billion by 2028 . For these platforms, the Recommendation Systems (RS) which can provide valuable assistance to job seekers by recommending suitable jobs, serve as their core components. Alone this line, considerable research efforts have been made in building RS for online recruitment [1]–[3] . Indeed, existing studies mainly follow the collaborative filter  \ning [1] or person-job matching paradigms [2], [3] . However,†Equal Contribution.  \n∗Corresponding authors.  \n1[https://www.theinsightpartners.com/reports/online-recruitment-market](https://www.theinsightpartners.com/reports/online-recruitment-market)  \nin practical applications, these methods will encounter the following challenges. First, these methods primarily rely on end-to-end neural network models, which usually output the matching score directly given the information of a specific job seeker and a job. Nevertheless, these models suffer from poor explainability in the black-box neural network computations, which reduce the user trust, especially in scenarios like job seeking that have a significant impact on individuals. Second, most of the existing models are discriminative model, which are li","cbCaioGGwlZUE8UC","https://ap.wps.com/l/cbCaioGGwlZUE8UC","pdf",717489,10,"English","# Abstract\n## Introduction","[{\"question\":\"Why do current job recommendation methods fall short for job seekers?\",\"answer\":\"They are commonly black-box matching models that provide limited explainability, and they focus on retrieving and ranking existing jobs rather than generating personalized guidance. This also leaves a semantic gap between CVs and job descriptions.\"},{\"question\":\"What is GIRL and how does it recommend jobs?\",\"answer\":\"GIRL is a generative job recommendation paradigm built on large language models. It generates job descriptions tailored to a job seeker using the seeker’s CV, instead of requiring a candidate job set.\"},{\"question\":\"How is GIRL trained to align with employer preferences?\",\"answer\":\"The method uses supervised fine-tuning to condition the generator on CV-to-JD creation, then trains a reward model for CV–JD matching and applies PPO-based reinforcement learning to optimize the generator using recruiter-aligned feedback.\"}]","Generative Job Recommendations with Large Language Model - GIRL | PDF",1789325116]