{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T15:26:31Z","timestamp":1780413991353,"version":"3.54.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Commission through the Horizon Europe Program through the Project \u201cReliable biomeTric tEchNologies to asSist Police authorities in cOmbating terrorism and oRganized crime (TENSOR)\u201d","award":["101073920"],"award-info":[{"award-number":["101073920"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3556973","type":"journal-article","created":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T21:58:37Z","timestamp":1743544717000},"page":"64087-64114","source":"Crossref","is-referenced-by-count":6,"title":["Exploring the Potential of Offline LLMs in Data Science: A Study on Code Generation for Data Analysis"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8054-5670","authenticated-orcid":false,"given":"Anastasios","family":"Nikolakopoulos","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Institute of Communication and Computer Systems, National Technical University of Athens, Zografou, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7658-2559","authenticated-orcid":false,"given":"Antonios","family":"Litke","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Institute of Communication and Computer Systems, National Technical University of Athens, Zografou, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0035-2885","authenticated-orcid":false,"given":"Alexandros","family":"Psychas","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Institute of Communication and Computer Systems, National Technical University of Athens, Zografou, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0946-4501","authenticated-orcid":false,"given":"Eleni","family":"Veroni","sequence":"additional","affiliation":[{"name":"Research and Innovation Development Department, Netcompany-Intrasoft S.A., Luxembourg, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodora","family":"Varvarigou","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Institute of Communication and Computer Systems, National Technical University of Athens, Zografou, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Gpt-4o Large Language Model","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1163\/9789004719118_050"},{"key":"ref3","article-title":"A comprehensive overview of large language models","author":"Naveed","year":"2023","journal-title":"arXiv:2307.06435"},{"key":"ref4","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref5","volume-title":"The impact of large language models on scientific discovery: A preliminary study using GPT-4","author":"AI4Science","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/EEITE61750.2024.10654427"},{"key":"ref7","article-title":"Challenges and applications of large language models","author":"Kaddour","year":"2023","journal-title":"arXiv:2307.10169"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeai.2023.100177"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2023.3265877"},{"key":"ref11","article-title":"Generalization through memorization: Nearest neighbor language models","author":"Khandelwal","year":"2019","journal-title":"arXiv:1911.00172"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0206-3"},{"issue":"140","key":"ref13","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-45072-3_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-024-03554-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3170427.3170632"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2819673"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC57700.2023.00117"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3617850"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584037"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-024-01373-8"},{"key":"ref22","volume-title":"Conala: The Code\/Natural Language Challenge","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ase.2015.36"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56957-9_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623316"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-024-04490-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-FoSE59343.2023.00008"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/e25060888"},{"key":"ref29","volume-title":"Github Copilot Ai Developer Tool","year":"2024"},{"key":"ref30","volume-title":"Deepmind Alphacode Ai Developer Tool","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MedAI59581.2023.00044"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-1711-8_12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3643681"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3660810"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56066-8_19"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.249"},{"key":"ref37","volume-title":"Ubiquitous knowledge processing lab (UKP-TUDA)","author":"Thakur","year":"2024"},{"key":"ref38","volume-title":"Trec 2020 Deep Learning Track","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-024-00252-z"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-023-00235-6"},{"key":"ref41","volume-title":"Openai Codex","year":"2024"},{"key":"ref42","volume-title":"Datarobot AI Solutions","year":"2024"},{"key":"ref43","volume-title":"Thoughtspot AI-Powered Analytics","year":"2024"},{"key":"ref44","volume-title":"Tableau Data Visualization","year":"2024"},{"key":"ref45","volume-title":"Microsoft Power BI","year":"2024"},{"key":"ref46","volume-title":"What is Prompt Engineering?","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7962-2_30"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15446\/dyna.v90n230.111700"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11528-023-00896-0"},{"key":"ref50","article-title":"A systematic survey of prompt engineering in large language models: Techniques and applications","author":"Sahoo","year":"2024","journal-title":"arXiv:2402.07927"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3591300"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63227-3_12"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11503"},{"key":"ref55","volume-title":"NETFLIX: Movies and Tv Shows Dataset","year":"2024"},{"key":"ref56","volume-title":"COVID-19 Twitter Dataset","year":"2024"},{"key":"ref57","volume-title":"Shard Cars Locations Dataset: Location History of Shared Cars","year":"2024"},{"key":"ref58","volume-title":"Autotel Project in Tel Aviv","year":"2024"},{"key":"ref59","volume-title":"Madrid Daily Weather Dataset: Daily Weather Conditions in Madrid from 1997\u20132015","year":"2024"},{"key":"ref60","volume-title":"Supermarket Sales Dataset: Historical Record of Sales Data in 3 Different Supermarkets","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3360306"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.55041\/ijsrem34001"},{"key":"ref63","volume-title":"Qwen 2.5 Coder Large Language Model","year":"2024"},{"key":"ref64","volume-title":"Humaneval Dataset","year":"2024"},{"key":"ref65","article-title":"RepoBench: Benchmarking repository-level code auto-completion systems","author":"Liu","year":"2023","journal-title":"arXiv:2306.03091"},{"key":"ref66","volume-title":"\u2018Cruxeval: Code Reasoning,\u2019 Understanding, and Execution Evaluation","year":"2024"},{"key":"ref67","volume-title":"Codellama: A State-of-the-Art Large Language Model for Coding","year":"2023"},{"key":"ref68","volume-title":"Deepseek Coder 33b Large Language Model","year":"2024"},{"key":"ref69","volume-title":"Llama 3: Openly Available Large Language Model","year":"2024"},{"key":"ref70","volume-title":"What is Mistral\u2019s Codestral? Key Features, Use Cases, and Limitations","year":"2024"},{"key":"ref71","article-title":"Qwen2.5-coder technical report","volume-title":"arXiv:2409.12186","author":"Hui","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.2196\/63731"},{"key":"ref73","volume-title":"Apache Spark: Unified Engine for Large-Scale Data Analytics","year":"2024"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-022-00196-2"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3390\/computers12110218"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076121"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58334-7_2"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00254"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.463"},{"key":"ref80","volume-title":"Hugging Face: Codestral V01 Large Language Model","year":"2024"},{"key":"ref81","volume-title":"Lm Studio Server","year":"2025"},{"key":"ref82","article-title":"The curious case of neural text degeneration","author":"Holtzman","year":"2019","journal-title":"arXiv:1904.09751"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13132454"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10947006.pdf?arnumber=10947006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T17:41:22Z","timestamp":1745257282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10947006\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3556973","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}