{"type":"ScholarlyArticle","title":"Using Large Language Models and Recruiter Expertise for Optimized Multilingual Job Offer – Applicant CV Matching","authors":[{"name":"Hamit Kavas","slug":"hamit-kavas","given":"Hamit","family":"Kavas","affiliation":"NLP Group , Pompeu Fabra University; Adevinta Spain"},{"name":"Marc Serra-Vidal","slug":"marc-serra-vidal","given":"Marc","family":"Serra-Vidal","affiliation":"Adevinta Spain"},{"name":"Leo Wanner","slug":"leo-wanner","given":"Leo","family":"Wanner","affiliation":"NLP Group , Pompeu Fabra University; Catalan Institute for Research and Advanced Studies (ICREA)"}],"abstract":"In the context of the increasingly globalised economy and labour market, recruitment agencies face the challenge to deal with a magnitude of job offers and job applications written in a variety of languages, formats, and styles. Quite often, this leads to a suboptimal evaluation of the CVs of job seekers with respect to their relevance to a job offer. To address this challenge, we propose an interactive system that follows the ``human-in-the-loop'' approach, actively involving recruiters in the job offer -- applicant CV matching. The system uses a fine-tuned state-of-the-art classification model that aligns job seeker CVs with labels of the {\\it European Skills, Competences, Qualifications and Occupations} taxonomy to propose an initial match between job offers with the CVs of job candidates. This match is refined in sequential LLM driven-interaction with the recruiter, which culminates in CV relevance scores and  reports that justify them.","doi":"10.24963/ijcai.2024/1011","url":"https://ijcai.org/proceedings/2024/1011","pdf":"https://ijcai.org/proceedings/2024/1011.pdf","markdown":"https://ijcai.org/proceedings/2024/1011.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/1011","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Demo Track","track":"Demo Track","number":1011,"pages":{"first":8696,"last":8699},"keywords":["Humans and AI: HAI: Human-AI collaboration","Machine Learning: ML: Applications","Natural Language Processing: NLP: Language models","Natural Language Processing: NLP: Applications","Natural Language Processing: NLP: Text classification"],"videos":[],"references":[{"position":1,"raw":"[Cai et al., 2023] Zefan Cai, Baobao Chang, and Wenjuan Han. Human-in-the-loop through chain-of-thought. ArXiv, abs/2306.07932, 2023.","title":"Human-in-the-loop through chain-of-thought","authors":"Zefan Cai, Baobao Chang, Wenjuan Han","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Clavié and Souli'e, 2023] Benjamin Clavié and Guillaume Souli'e. Large language models as batteries-included zero- shot esco skills matchers. ArXiv, abs/2307.03539, 2023.","title":"Large language models as batteries-included zeroshot esco skills matchers","authors":"Souli Clavié, Benjamin Clavié, Guillaume Souli, '","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Colucci et al., 2003] Simona Colucci, Tommaso Di Noia, Eugenio Di Sciascio, Francesco Donini, Marina Mongiello, and Marco Mottola. A formal approach to ontology-based semantic match of skills descriptions. J. UCS, 9:1437-1454, 01 2003.","title":"A formal approach to ontology-based semantic match of skills descriptions","authors":"Simona Colucci, Tommaso Di Noia, Eugenio Di Sciascio, Francesco Donini, Marina Mongiello, Marco Mottola","year":"2003","venue":"J. UCS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dover, 2023] Dover. Home page. https://www.dover.com/, 2023. Accessed: 20-02-2024.","title":"Dover. Home page","authors":null,"year":"2023","venue":null,"doi":null,"url":"https://www.dover.com/,2023","internal_url":null},{"position":5,"raw":"[Greenhouse, 2023] Greenhouse. Home page. https://www. greenhouse.com/uk, 2023. Accessed: 20-02-2024.","title":"Greenhouse. Home page","authors":"Greenhouse","year":"2023","venue":null,"doi":null,"url":"https://www.greenhouse.com/uk,2023","internal_url":null},{"position":6,"raw":"[HireVue, 2023] HireVue. Home page. https://www.hirevue. com/, 2023. Accessed: 20-02-2024.","title":"HireVue. Home page","authors":null,"year":"2023","venue":null,"doi":null,"url":"https://www.hirevue.com/,2023","internal_url":null},{"position":7,"raw":"[Jiang et al., 2024] Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, L'elio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon An- toniak, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, and William El Sayed. Mixtral of experts. ArXiv, abs/2401.04088, 2024.","title":"Mixtral of experts","authors":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego De Las, Emma Bou Casas, Florian Hanna, Gianna Bressand, Guillaume Lengyel, Guillaume Bour, L' Lample, Renard Elio, Lucile Lavaud, Marie-Anne Saulnier, Pierre Lachaux, Sandeep Stock, Sophia Subramanian, Szymon Yang, Teven Antoniak, Théophile Le Scao, Thibaut Gervet, Thomas Lavril, Timothée Wang, William El Lacroix, Sayed","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kavas et al., 2023] Hamit Kavas, Marc Serra-vidal, and Leo Wanner. Job offer and applicant cv classification using rich information from a labour market taxonomy. SSRN Electronic Journal, 2023.","title":"Job offer and applicant cv classification using rich information from a labour market taxonomy","authors":"Hamit Kavas, Marc Serra-Vidal, Leo Wanner","year":"2023","venue":"SSRN Electronic Journal","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Koh et al., 2023] Nam Ho Koh, Joseph Plata, and Joyce Chai. Bad: Bias detection for large language models in the context of candidate screening. ArXiv, abs/2305.10407, 2023.","title":"Bad: Bias detection for large language models in the context of candidate screening","authors":"Koh","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lever, 2023] Lever. Home page. https://www.lever.co/, 2023. Accessed: 20-02-2024.","title":"Lever. Home page","authors":"Lever","year":"2023","venue":null,"doi":null,"url":"https://www.lever.co/,2023","internal_url":null},{"position":11,"raw":"[Lewis et al., 2020] Patrick Lewis, Ethan Perez, Aleksan- dra Piktus, Fabio Petroni, Vladimir Karpukhin, Na- man Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. Retrieval-augmented generation for knowledge-intensive nlp tasks. In Proceedings of the 34th International Confer- ence on Neural Information Processing Systems, NIPS'20, Red Hook, NY, USA, 2020.","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","authors":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-Tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela","year":"2020","venue":"Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS'20","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Curran Associates Inc. Li et al., 2023] Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. To- wards general text embeddings with multi-stage con- trastive learning. ArXiv, abs/2308.03281, 2023.","title":"Towards general text embeddings with multi-stage contrastive learning","authors":"Curran Associates, Inc Li","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Magron et al., 2024] Antoine Magron, Anna Dai, Mike Zhang, Syrielle Montariol, and Antoine Bosselut. Job- skape: A framework for generating synthetic job postings to enhance skill matching. ArXiv, abs/2402.03242, 2024.","title":"Jobskape: A framework for generating synthetic job postings to enhance skill matching","authors":"Antoine Magron, Anna Dai, Mike Zhang, Syrielle Montariol, Antoine Bosselut","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Nguyen et al., 2024] Khanh Cao Nguyen, Mike Zhang, Syrielle Montariol, and Antoine Bosselut. Rethinking skill extraction in the job market domain using large language models. ArXiv, abs/2402.03832, 2024.","title":"Rethinking skill extraction in the job market domain using large language models","authors":"Cao Khanh, Mike Nguyen, Syrielle Zhang, Antoine Montariol, Bosselut","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Wang et al., 2024a] Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. Multilingual e5 text embeddings: A technical report. ArXiv, abs/2402.05672, 2024.","title":"Multilingual e5 text embeddings: A technical report","authors":"Wang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wang et al., 2024b] Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. Multilingual e5 text embeddings: A technical report. ArXiv, abs/2402.05672, 2024.","title":"Multilingual e5 text embeddings: A technical report","authors":"Wang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Workable, 2023] Workable. Home page. https://www. workable.com/, 2023. Accessed: 20-02-2024.","title":"Workable. Home page","authors":"Workable","year":"2023","venue":null,"doi":null,"url":"https://www.workable.com/,2023","internal_url":null},{"position":18,"raw":"[Yu et al., 2024] Xiao Yu, Jinzhong Zhang, and Zhou Yu. Confit: Improving resume-job matching using data augmentation and contrastive learning. ArXiv, abs/2401.16349, 2024.","title":"Confit: Improving resume-job matching using data augmentation and contrastive learning","authors":"Xiao Yu, Jinzhong Zhang, Zhou Yu","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Zhang et al., 2024] Mike Zhang, Rob van der Goot, and Barbara Plank. Entity linking in the job market domain. ArXiv, abs/2401.17979, 2024.","title":"Entity linking in the job market domain","authors":"Mike Zhang, Rob Van Der Goot, Barbara Plank","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zheng et al., 2023] Zhi Zheng, Zhaopeng Qiu, Xiao Hu, Likang Wu, Hengshu Zhu, and Hui Xiong. Generative job recommendations with large language model. ArXiv, abs/2307.02157, 2023.","title":"Generative job recommendations with large language model","authors":"Zhi Zheng, Zhaopeng Qiu, Xiao Hu, Likang Wu, Hengshu Zhu, Hui Xiong","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zinjad et al., 2024] Saurabh Bhausaheb Zinjad, Amrita Bhattacharjee, Amey Bhilegaonkar, and Huan Liu. Re- sumeflow: An llm-facilitated pipeline for personalized re- sume generation and refinement. ArXiv, abs/2402.06221, 2024.","title":"Resumeflow: An llm-facilitated pipeline for personalized resume generation and refinement","authors":"Saurabh Bhausaheb Zinjad, Amrita Bhattacharjee, Amey Bhilegaonkar, Huan Liu","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}