{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T15:59:24Z","timestamp":1765468764679,"version":"3.48.0"},"reference-count":65,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"name":"Swiss National Science Foundation for the PARSED project","award":["219294"],"award-info":[{"award-number":["219294"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,1,31]]},"abstract":"<jats:p>\n                    Deep learning (DL)-based code completion tools have revolutionized software development by providing unprecedented code generation capabilities. The DL models behind these tools are usually trained on large amounts of code from thousands of software repositories. This makes them good in learning\n                    <jats:italic toggle=\"yes\">natural<\/jats:italic>\n                    coding patterns observed across many training instances. However, little is known about the extent to which additional training effort (fine-tuning) aimed at specializing the models towards the code base of a given organization\/developer further benefits their code completion capabilities. In this work, we fill this gap by presenting solid empirical evidence answering this question. More specifically, we consider 136 developers from two organizations (Apache and Spring), two model architectures (T5 and Code Llama), and three model sizes (60M, 750M, and 7B trainable parameters). For T5 models (60M and 750M), we pre-train and fine-tune them on over 2,000 open source projects, making sure that code from the two subject organizations is not part of their training sets. Then, we compare their completion capabilities against the same models further fine-tuned on organization- and developer-specific datasets. For the Code Llama model (7B), we compare the performance of the already pre-trained model publicly available online with the same model fine-tuned via parameter-efficient fine-tuning on organization- and developer-specific datasets. Our results show that there is a boost in prediction capabilities provided by both an organization-specific and a developer-specific additional fine-tuning, with the former being particularly performant. Such a finding generalizes across (i) the two subject organizations (i.e., Apache and Spring) and (ii) models of completely different magnitude (from 60M to 7B trainable parameters). Finally, we show that DL models fine-tuned on an organization-specific dataset achieve the same completion performance of pre-trained code models used out of the box and being\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\sim\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    10\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    larger, with consequent savings in terms of deployment and inference cost (e.g., smaller GPUs needed).\n                  <\/jats:p>","DOI":"10.1145\/3725732","type":"journal-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:56:19Z","timestamp":1742990179000},"page":"1-37","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Why Personalizing Deep Learning-Based Code Completion Tools Matters"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3454-3349","authenticated-orcid":false,"given":"Alessandro","family":"Giagnorio","sequence":"first","affiliation":[{"name":"Universit\u00e0 della Svizzera italiana, Lugano, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5501-9225","authenticated-orcid":false,"given":"Alberto","family":"Martin-Lopez","sequence":"additional","affiliation":[{"name":"Universit\u00e0 della Svizzera italiana, Lugano, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2216-3148","authenticated-orcid":false,"given":"Gabriele","family":"Bavota","sequence":"additional","affiliation":[{"name":"Faculty of Informatics, Universit\u00e0 della Svizzera Italiana, Lugano, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,11]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"GitHub. 2024. Apache Commons BeanUtils. Retrieved March 5 2024 from https:\/\/github.com\/apache\/commons-beanutils\/"},{"key":"e_1_3_2_3_2","unstructured":"Hugging Face. 2024. CodeParrot GitHub Code Dataset. Retrieved February 8 2024 from https:\/\/huggingface.co\/datasets\/codeparrot\/github-code"},{"key":"e_1_3_2_4_2","unstructured":"GitHub. 2024. GitHub Copilot\u2014Your AI Pair Programmer. Retrieved March 10 2024 from https:\/\/github.com\/features\/copilot\/"},{"key":"e_1_3_2_5_2","unstructured":"PyPI. 2024. javalang\u2014PyPI. Retrieved February 8 2024 from https:\/\/pypi.org\/project\/javalang\/"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Alessandro Giagnorio Alberto Martin-Lopez and Gabriele Bavota. 2024. Replication Package. DOI: 10.5281\/zenodo.10817220","DOI":"10.5281\/zenodo.10817220"},{"key":"e_1_3_2_7_2","unstructured":"Hugging Face. 2024. T5v1.1. Retrieved February 8 2024 from https:\/\/huggingface.co\/docs\/transformers\/en\/model_doc\/t5v1.1"},{"key":"e_1_3_2_8_2","unstructured":"Microsoft. 2024. Microsoft Fiscal Year 2024 Second Quarter Earnings Conference Call. Retrieved February 2 2024 from https:\/\/www.microsoft.com\/en-us\/investor\/events\/fy-2024\/earnings-fy-2024-q2.aspx"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3559555"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639183"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2635868.2635883"},{"key":"e_1_3_2_12_2","first-page":"245","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Alon Uri","year":"2020","unstructured":"Uri Alon, Roy Sadaka, Omer Levy, and Eran Yahav. 2020. Structural language models of code. In Proceedings of the International Conference on Machine Learning (ICML), 245\u2013256."},{"key":"e_1_3_2_13_2","first-page":"621","volume-title":"Proceedings of the 30th IEEE International Conference on Software Maintenance and Evolution (ICSME)","author":"Asaduzzaman Muhammad","year":"2014","unstructured":"Muhammad Asaduzzaman, Chanchal K. Roy, Kevin A. Schneider, and Daqing Hou. 2014. Context-sensitive code completion tool for better API usability. In Proceedings of the 30th IEEE International Conference on Software Maintenance and Evolution (ICSME), 621\u2013624."},{"key":"e_1_3_2_14_2","unstructured":"Ramakrishna Bairi Atharv Sonwane Aditya Kanade Vageesh D. C. Arun Iyer Suresh Parthasarathy Sriram Rajamani B. Ashok and Shashank Shet. 2023. CodePlan: Repository-level coding using LLMs and planning. arXiv:2309.12499. Retrieved from https:\/\/arxiv.org\/abs\/2309.12499"},{"key":"e_1_3_2_15_2","first-page":"780","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Berabi Berkay","year":"2021","unstructured":"Berkay Berabi, Jingxuan He, Veselin Raychev, and Martin Vechev. 2021. TFix: Learning to fix coding errors with a text-to-text transformer. In Proceedings of the 38th International Conference on Machine Learning. Marina Meila and Tong Zhang (Eds.), Proceedings of Machine Learning Research, Vol. 139, PMLR, 780\u2013791."},{"key":"e_1_3_2_16_2","first-page":"213","volume-title":"Proceedings of the 7th ACM Joint Meeting of the European Software Engineering Conference and the ACM\/SIGSOFT International Symposium on Foundations of Software Engineering (ESEC-FSE)","author":"Bruch Marcel","year":"2009","unstructured":"Marcel Bruch, Martin Monperrus, and Mira Mezini. 2009. Learning from examples to improve code completion systems. In Proceedings of the 7th ACM Joint Meeting of the European Software Engineering Conference and the ACM\/SIGSOFT International Symposium on Foundations of Software Engineering (ESEC-FSE), 213\u2013222."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689735"},{"key":"e_1_3_2_18_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et al. 2021. Evaluating large language models trained on code. arXiv:2107.03374. Retrieved from https:\/\/arxiv.org\/abs\/2107.03374"},{"issue":"12","key":"e_1_3_2_19_2","first-page":"4818","article-title":"An empirical study on the usage of transformer models for code completion","volume":"48","author":"Ciniselli Matteo","year":"2022","unstructured":"Matteo Ciniselli, Nathan Cooper, Luca Pascarella, Antonio Mastropaolo, Emad Aghajani, Denys Poshyvanyk, Massimiliano Di Penta, and Gabriele Bavota. 2022. An empirical study on the usage of transformer models for code completion. IEEE Transactions on Software Engineering 48, 12 (2022), 4818\u20134837.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_20_2","first-page":"108","volume-title":"Proceedings of the 18th IEEE\/ACM International Conference on Mining Software Repositories (MSR \u201921)","author":"Ciniselli Matteo","year":"2021","unstructured":"Matteo Ciniselli, Nathan Cooper, Luca Pascarella, Denys Poshyvanyk, Massimiliano Di Penta, and Gabriele Bavota. 2021. An empirical study on the usage of BERT models for code completion. In Proceedings of the 18th IEEE\/ACM International Conference on Mining Software Repositories (MSR \u201921), 108\u2013119."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528440"},{"key":"e_1_3_2_22_2","first-page":"560","volume-title":"Proceedings of the 18th IEEE\/ACM International Conference on Mining Software Repositories (MSR)","author":"Dabic Ozren","year":"2021","unstructured":"Ozren Dabic, Emad Aghajani, and Gabriele Bavota. 2021. Sampling projects in GitHub for MSR studies. In Proceedings of the 18th IEEE\/ACM International Conference on Mining Software Repositories (MSR), 560\u2013564."},{"key":"e_1_3_2_23_2","first-page":"4171","volume-title":"Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 4171\u20134186."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556903"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2021.3133805"},{"key":"e_1_3_2_26_2","first-page":"610","volume-title":"Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)","author":"Eschbach-Dymanus Johannes","year":"2024","unstructured":"Johannes Eschbach-Dymanus, Frank Essenberger, Bianka Buschbeck, and Miriam Exel. 2024. Exploring the effectiveness of LLM domain adaptation for business IT machine translation. In Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1). Carolina Scarton, Charlotte Prescott, Chris Bayliss, Chris Oakley, Joanna Wright, Stuart Wrigley, Xingyi Song, Edward Gow-Smith, Rachel Bawden, V\u00edctor M. S\u00e1nchez-Cartagena, et al. (Eds.), 610\u2013622."},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Zhangyin Feng Daya Guo Duyu Tang Nan Duan Xiaocheng Feng Ming Gong Linjun Shou Bing Qin Ting Liu Daxin Jiang et al. 2020. CodeBERT: A pre-trained model for programming and natural languages. arXiv:2002.08155. Retrieved from https:\/\/arxiv.org\/abs\/2002.08155","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSCC51209.2021.9528123"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR52588.2021.00021"},{"key":"e_1_3_2_30_2","volume-title":"Effect Sizes for Research: A Broad Practical Approach","author":"Grissom Robert J.","year":"2005","unstructured":"Robert J. Grissom and John J. Kim. 2005. Effect Sizes for Research: A Broad Practical Approach (2nd. ed.). Lawrence Erlbaum Associates.","edition":"2"},{"key":"e_1_3_2_31_2","first-page":"763","volume-title":"Proceedings of the 11th ACM\/SIGSOFT Joint Meeting on Foundations of Software Engineering (ESEC-FSE)","author":"Hellendoorn Vincent J.","year":"2017","unstructured":"Vincent J. Hellendoorn and Premkumar Devanbu. 2017. Are deep neural networks the best choice for modeling source code? In Proceedings of the 11th ACM\/SIGSOFT Joint Meeting on Foundations of Software Engineering (ESEC-FSE), 763\u2013773."},{"key":"e_1_3_2_32_2","first-page":"960","volume-title":"Proceedings of the 41st IEEE\/ACM International Conference on Software Engineering (ICSE)","author":"Hellendoorn Vincent J.","year":"2019","unstructured":"Vincent J. Hellendoorn, Sebastian Proksch, Harald C. Gall, and Alberto Bacchelli. 2019. When code completion fails: A case study on real-world completions. In Proceedings of the 41st IEEE\/ACM International Conference on Software Engineering (ICSE), 960\u2013970."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.5555\/2337223.2337322"},{"key":"e_1_3_2_34_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_35_2","first-page":"367","volume-title":"Proceedings of the 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE)","author":"Huang Kai","year":"2024","unstructured":"Kai Huang, Jian Zhang, Xiangxin Meng, and Yang Liu. 2024. Template-guided program repair in the era of large language models. In Proceedings of the 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE). IEEE Computer Society, 367\u2013379."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510454.3522684"},{"key":"e_1_3_2_37_2","first-page":"401","volume-title":"Proceedings of the 44th IEEE\/ACM International Conference on Software Engineering (ICSE)","author":"Izadi Maliheh","year":"2022","unstructured":"Maliheh Izadi, Roberta Gismondi, and Georgios Gousios. 2022. CodeFill: Multi-token code completion by jointly learning from structure and naming sequences. In Proceedings of the 44th IEEE\/ACM International Conference on Software Engineering (ICSE), 401\u2013412."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639138"},{"key":"e_1_3_2_39_2","first-page":"70","volume-title":"Proceedings of the 15th IEEE\/ACM International Conference on Mining Software Repositories (MSR)","author":"Jin Xianhao","year":"2018","unstructured":"Xianhao Jin and Francisco Servant. 2018. The hidden cost of code completion: Understanding the impact of the recommendation-list length on its efficiency. In Proceedings of the 15th IEEE\/ACM International Conference on Mining Software Repositories (MSR), 70\u201373."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416591"},{"issue":"4","key":"e_1_3_2_41_2","doi-asserted-by":"crossref","first-page":"1268","DOI":"10.1109\/TSE.2020.3018481","article-title":"Deep learning based program generation from requirements text: Are we there yet","volume":"48","author":"Liu Hui","year":"2020","unstructured":"Hui Liu, Mingzhu Shen, Jiaqi Zhu, Nan Niu, Ge Li, and Lu Zhang. 2020. Deep learning based program generation from requirements text: Are we there yet? IEEE Transactions on Software Engineering 48, 4 (2020), 1268\u20131289.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_42_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR)","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In Proceedings of the 7th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_43_2","volume-title":"Proceedings of the 35th Neural Information Processing Systems Track on Datasets and Benchmarks 1 (NeurIPS Datasets and Benchmarks)","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin B. Clement, Dawn Drain, Daxin Jiang, Duyu Tang, et al. 2021. CodeXGLUE: A machine learning benchmark dataset for code understanding and generation. In Proceedings of the 35th Neural Information Processing Systems Track on Datasets and Benchmarks 1 (NeurIPS Datasets and Benchmarks)."},{"key":"e_1_3_2_44_2","first-page":"14","volume-title":"Proceedings of the 26th Annual Workshop of the Psychology of Programming Interest Group (PPIG)","author":"Marasoiu Mariana","year":"2015","unstructured":"Mariana Marasoiu, Luke Church, and Alan F. Blackwell. 2015. An empirical investigation of code completion usage by professional software developers. In Proceedings of the 26th Annual Workshop of the Psychology of Programming Interest Group (PPIG), 14."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3183297"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00181"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02295996"},{"key":"e_1_3_2_48_2","first-page":"7","article-title":"Recommending API function calls and code snippets to support software development","volume":"48","author":"Nguyen Phuong T.","year":"2022","unstructured":"Phuong T. Nguyen, Juri Di Rocco, Claudio Di Sipio, Davide Di Ruscio, and Massimiliano Di Penta. 2022. Recommending API function calls and code snippets to support software development. IEEE Transactions on Software Engineering 48, 7 (2022), 2417\u20132438.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_49_2","first-page":"311","volume-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics (ACL)","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics (ACL), 311\u2013318."},{"key":"e_1_3_2_50_2","unstructured":"Sida Peng Eirini Kalliamvakou Peter Cihon and Mert Demirer. 2023. The impact of AI on developer productivity: Evidence from GitHub Copilot. arXiv:2302.06590. Retrieved from https:\/\/arxiv.org\/abs\/2302.06590"},{"issue":"140","key":"e_1_3_2_51_2","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research 21, 140 (2020), 1\u201367. Retrieved from http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10515-010-0064-x"},{"key":"e_1_3_2_53_2","unstructured":"Baptiste Roziere Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Tal Remez J\u00e9r\u00e9my Rapin et al. 2023. Code Llama: Open foundation models for code. arXiv:2308.12950. Retrieved from https:\/\/arxiv.org\/abs\/2308.12950"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2804431"},{"key":"e_1_3_2_55_2","first-page":"419","volume-title":"Proceedings of the 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE)","author":"Sun Weisong","year":"2024","unstructured":"Weisong Sun, Yun Miao, Yuekang Li, Hongyu Zhang, Chunrong Fang, Yi Liu, Gelei Deng, Yang Liu, and Zhenyu Chen. 2024. Source code summarization in the era of large language models. In Proceedings of the 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE). IEEE Computer Society, 419\u2013431."},{"key":"e_1_3_2_56_2","first-page":"329","volume-title":"Proceedings of the 18th IEEE\/ACM International Conference on Mining Software Repositories (MSR)","author":"Svyatkovskiy Alexey","year":"2021","unstructured":"Alexey Svyatkovskiy, Sebastian Lee, Anna Hadjitofi, Maik Riechert, Juliana Vicente Franco, and Miltiadis Allamanis. 2021. Fast and memory-efficient neural code completion. In Proceedings of the 18th IEEE\/ACM International Conference on Mining Software Repositories (MSR), 329\u2013340."},{"key":"e_1_3_2_57_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510621"},{"key":"e_1_3_2_59_2","doi-asserted-by":"crossref","unstructured":"Yue Wang Weishi Wang Shafiq Joty and Steven C. H. Hoi. 2021. CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv:2109.00859. Retrieved from https:\/\/arxiv.org\/abs\/2109.00859","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_2_60_2","unstructured":"Martin Weyssow Xin Zhou Kisub Kim David Lo and Houari Sahraoui. 2023. Exploring parameter-efficient fine-tuning techniques for code generation with large language models. arXiv:2308.10462. Retrieved from https:\/\/arxiv.org\/abs\/2308.10462"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.2307\/3001968"},{"key":"e_1_3_2_62_2","doi-asserted-by":"crossref","unstructured":"Frank F. Xu Bogdan Vasilescu and Graham Neubig. 2022. In-IDE code generation from natural language: Promise and challenges. ACM Transactions on Software Engineering and Methodology 31 2 (2022) 29:1\u201329:47.","DOI":"10.1145\/3487569"},{"key":"e_1_3_2_63_2","doi-asserted-by":"crossref","unstructured":"Fengji Zhang Bei Chen Yue Zhang Jin Liu Daoguang Zan Yi Mao Jian-Guang Lou and Weizhu Chen. 2023. RepoCoder: Repository-level code completion through iterative retrieval and generation. arXiv:2303.12570. Retrieved from https:\/\/arxiv.org\/abs\/2303.12570","DOI":"10.18653\/v1\/2023.emnlp-main.151"},{"key":"e_1_3_2_64_2","unstructured":"Albert Ziegler. 2022. GitHub Copilot Research Recitation. Retrieved November 10 2024 from https:\/\/github.blog\/ai-and-ml\/github-copilot\/github-copilot-research-recitation\/"},{"key":"e_1_3_2_65_2","first-page":"21","volume-title":"Proceedings of the International Symposium on Machine Programming","author":"Ziegler Albert","year":"2022","unstructured":"Albert Ziegler, Eirini Kalliamvakou, X. Alice Li, Andrew Rice, Devon Rifkin, Shawn Simister, Ganesh Sittampalam, and Edward Aftandilian. 2022. Productivity assessment of neural code completion. In Proceedings of the International Symposium on Machine Programming, 21\u201329."},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3558959"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T15:56:28Z","timestamp":1765468588000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,11]]},"references-count":65,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3725732"],"URL":"https:\/\/doi.org\/10.1145\/3725732","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"type":"print","value":"1049-331X"},{"type":"electronic","value":"1557-7392"}],"subject":[],"published":{"date-parts":[[2025,12,11]]},"assertion":[{"value":"2024-07-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}