{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T02:19:52Z","timestamp":1776824392405,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":86,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Research Foundation, Singapore","award":["NRF-NRFI08-2022-0002"],"award-info":[{"award-number":["NRF-NRFI08-2022-0002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1145\/3639475.3640097","type":"proceedings-article","created":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T12:37:31Z","timestamp":1717677451000},"page":"142-153","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Greening Large Language Models of Code"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0799-5018","authenticated-orcid":false,"given":"Jieke","family":"Shi","sequence":"first","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5938-1918","authenticated-orcid":false,"given":"Zhou","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7335-7295","authenticated-orcid":false,"given":"Hong Jin","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California, Los Angeles, Los Angeles, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1006-8493","authenticated-orcid":false,"given":"Bowen","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, North Carolina State University, Raleigh, North Carolina, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-8585","authenticated-orcid":false,"given":"Junda","family":"He","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4367-7201","authenticated-orcid":false,"given":"David","family":"Lo","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2024,6,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238192"},{"key":"e_1_3_2_1_2_1","unstructured":"Akvelon. 2023. Code Search: a Closer Look at Akvelon's Source Code Search Engine --- akvelon.com. https:\/\/akvelon.com\/code-search-a-closer-look-at-akvelons-source-code-search-engine\/. [Accessed 28-09-2023]."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1985793.1985795"},{"key":"e_1_3_2_1_4_1","volume-title":"Sequence model design for code completion in the modern IDE. arXiv preprint arXiv:2004.05249","author":"Aye Gareth Ari","year":"2020","unstructured":"Gareth Ari Aye and Gail E Kaiser. 2020. Sequence model design for code completion in the modern IDE. arXiv preprint arXiv:2004.05249 (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems-Volume 2. 2654--2662","author":"Ba Lei Jimmy","year":"2014","unstructured":"Lei Jimmy Ba and Rich Caruana. 2014. Do deep nets really need to be deep?. In Proceedings of the 27th International Conference on Neural Information Processing Systems-Volume 2. 2654--2662."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39611-3_3"},{"key":"e_1_3_2_1_7_1","volume-title":"Deep learning based vulnerability detection: Are we there yet","author":"Chakraborty Saikat","year":"2021","unstructured":"Saikat Chakraborty, Rahul Krishna, Yangruibo Ding, and Baishakhi Ray. 2021. Deep learning based vulnerability detection: Are we there yet. IEEE Transactions on Software Engineering (2021)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/341"},{"key":"e_1_3_2_1_9_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","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 preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3514233","article-title":"The weights can be harmful: Pareto search versus weighted search in multi-objective search-based software engineering","volume":"32","author":"Chen Tao","year":"2023","unstructured":"Tao Chen and Miqing Li. 2023. The weights can be harmful: Pareto search versus weighted search in multi-objective search-based software engineering. ACM Transactions on Software Engineering and Methodology 32, 1 (2023), 1--40.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/1792734.1792766"},{"key":"e_1_3_2_1_12_1","unstructured":"GitLab Auto DevOps. 2023. Top 10 ways machine learning may help DevOps --- about.gitlab.com. https:\/\/about.gitlab.com\/blog\/2022\/02\/14\/top-10-ways-machine-learning-may-help-devops\/. [Accessed 22-09-2023]."},{"key":"e_1_3_2_1_13_1","volume-title":"Sea Change in Software Development: Economic and Productivity Analysis of the AI-Powered Developer Lifecycle. arXiv preprint arXiv:2306.15033","author":"Dohmke Thomas","year":"2023","unstructured":"Thomas Dohmke, Marco Iansiti, and Greg Richards. 2023. Sea Change in Software Development: Economic and Productivity Analysis of the AI-Powered Developer Lifecycle. arXiv preprint arXiv:2306.15033 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural networks 107","author":"Elfwing Stefan","year":"2018","unstructured":"Stefan Elfwing, Eiji Uchibe, and Kenji Doya. 2018. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural networks 107 (2018), 3--11."},{"key":"e_1_3_2_1_15_1","unstructured":"Hugging Face. 2023. Configurations of Encoder-only Models --- huggingface.co. https:\/\/huggingface.co\/docs\/transformers\/model_doc\/roberta#transformers.RobertaConfig. [Accessed 25-09-2023]."},{"key":"e_1_3_2_1_16_1","volume-title":"Reducing Transformer Depth on Demand with Structured Dropout. In 2020 8th International Conference on Learning Representations.","author":"Fan Angela","year":"2020","unstructured":"Angela Fan, Edouard Grave, and Armand Joulin. 2020. Reducing Transformer Depth on Demand with Structured Dropout. In 2020 8th International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16493-4_19"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_19_1","volume-title":"Yin Yang, Hassan Sajjad, Preslav Nakov, Deming Chen, and Marianne Winslett.","author":"Ganesh Prakhar","year":"2021","unstructured":"Prakhar Ganesh, Yao Chen, Xin Lou, Mohammad Ali Khan, Yin Yang, Hassan Sajjad, Preslav Nakov, Deming Chen, and Marianne Winslett. 2021. Compressing Large-Scale Transformer-Based Models: A Case Study on BERT. Transactions of the Association for Computational Linguistics 9 (09 2021), 1061--1080."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP58684.2023.00039"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00028"},{"key":"e_1_3_2_1_22_1","unstructured":"GitHub. 2023. GitHub Copilot Community. https:\/\/github.com\/orgs\/community\/discussions\/categories\/copilot?discussions_q=category%3ACopilot+network. [Accessed 03-10-2023]."},{"key":"e_1_3_2_1_23_1","unstructured":"GitHub. 2023. GitHub Copilot \u00b7 Your AI pair programmer --- github.com. https:\/\/github.com\/features\/copilot\/. [Accessed 22-09-2023]."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_25_1","volume-title":"The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification. arXiv preprint arXiv:2305.04940","author":"Grishina Anastasiia","year":"2023","unstructured":"Anastasiia Grishina, Max Hort, and Leon Moonen. 2023. The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification. arXiv preprint arXiv:2305.04940 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"2021 9th International Conference on Learning Representations.","author":"Guo Daya","year":"2021","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie LIU, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, and Ming Zhou. 2021. GraphCode{BERT}: Pre-training Code Representations with Data Flow. In 2021 9th International Conference on Learning Representations."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-017-9573-6"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00113"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510088"},{"key":"e_1_3_2_1_30_1","volume-title":"Analysis of function of rectified linear unit used in deep learning. In 2015 international joint conference on neural networks (IJCNN)","author":"Hara Kazuyuki","unstructured":"Kazuyuki Hara, Daisuke Saito, and Hayaru Shouno. 2015. Analysis of function of rectified linear unit used in deep learning. In 2015 international joint conference on neural networks (IJCNN). IEEE, 1--8."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00101"},{"key":"e_1_3_2_1_32_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3527949"},{"key":"e_1_3_2_1_34_1","volume-title":"2015 NIPS Deep Learning and Representation Learning Workshop.","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. In 2015 NIPS Deep Learning and Representation Learning Workshop."},{"key":"e_1_3_2_1_35_1","volume-title":"Large Language Models for Software Engineering: A Systematic Literature Review. arXiv preprint arXiv:2308.10620","author":"Hou Xinyi","year":"2023","unstructured":"Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, and Haoyu Wang. 2023. Large Language Models for Software Engineering: A Systematic Literature Review. arXiv preprint arXiv:2308.10620 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Do Not Give Away My Secrets: Uncovering the Privacy Issue of Neural Code Completion Tools. arXiv preprint arXiv:2309.07639","author":"Huang Yizhan","year":"2023","unstructured":"Yizhan Huang, Yichen Li, Weibin Wu, Jianping Zhang, and Michael R Lyu. 2023. Do Not Give Away My Secrets: Uncovering the Privacy Issue of Neural Code Completion Tools. arXiv preprint arXiv:2309.07639 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"Improve Transformer Models with Better Relative Position Embeddings. Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Huang Zhiheng","year":"2020","unstructured":"Zhiheng Huang, Davis Liang, Peng Xu, and Bing Xiang. 2020. Improve Transformer Models with Better Relative Position Embeddings. Findings of the Association for Computational Linguistics: EMNLP 2020 (2020)."},{"key":"e_1_3_2_1_38_1","volume-title":"Codesearchnet challenge: Evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436","author":"Husain Hamel","year":"2019","unstructured":"Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit, Miltiadis Allamanis, and Marc Brockschmidt. 2019. Codesearchnet challenge: Evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436 (2019)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593434.3594236"},{"key":"e_1_3_2_1_40_1","unstructured":"Apple Inc. 2023. MacBook Pro 14- and 16-inch - Tech Specs --- apple.com. https:\/\/www.apple.com\/sg\/macbook-pro-14-and-16\/specs\/. [Accessed 03-10-2023]."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380342"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"5518","author":"Kim Sehoon","year":"2021","unstructured":"Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, and Kurt Keutzer. 2021. I-BERT: Integer-only BERT Quantization. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139). PMLR, 5506--5518."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2017913370"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"e_1_3_2_1_46_1","volume-title":"Quantifying the Carbon Emissions of Machine Learning. arXiv preprint arXiv:1910.09700","author":"Lacoste Alexandre","year":"2019","unstructured":"Alexandre Lacoste, Alexandra Luccioni, Victor Schmidt, and Thomas Dandres. 2019. Quantifying the Carbon Emissions of Machine Learning. arXiv preprint arXiv:1910.09700 (2019)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416591"},{"key":"e_1_3_2_1_48_1","volume-title":"Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps. arXiv preprint arXiv:2309.04142","author":"David Lo.","year":"2023","unstructured":"David Lo. 2023. Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps. arXiv preprint arXiv:2309.04142 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. In 35th Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, Duyu Tang, Ge Li, Lidong Zhou, Linjun Shou, Long Zhou, Michele Tufano, MING GONG, Ming Zhou, Nan Duan, Neel Sundaresan, Shao Kun Deng, Shengyu Fu, and Shujie LIU. 2021. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. In 35th Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)."},{"key":"e_1_3_2_1_50_1","unstructured":"Sean Luke. 2009. Essentials of metaheuristics."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.415"},{"key":"e_1_3_2_1_52_1","volume-title":"An Empirical Study of Practitioners' Perspectives on Green Software Engineering. In 2016 IEEE\/ACM 38th International Conference on Software Engineering (ICSE). 237--248","author":"Manotas Irene","year":"2016","unstructured":"Irene Manotas, Christian Bird, Rui Zhang, David Shepherd, Ciera Jaspan, Caitlin Sadowski, Lori Pollock, and James Clause. 2016. An Empirical Study of Practitioners' Perspectives on Green Software Engineering. In 2016 IEEE\/ACM 38th International Conference on Software Engineering (ICSE). 237--248."},{"key":"e_1_3_2_1_53_1","unstructured":"Ivan Mehta. 2023. Apple reportedly limits internal use of AI-powered tools | TechCrunch. https:\/\/techcrunch.com\/2023\/05\/19\/apple-reportedly-limits-internal-use-of-ai-powered-tools-like-chatgpt-and-github-copilot. [Accessed 03-10-2023]."},{"key":"e_1_3_2_1_54_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Michel Paul","year":"2019","unstructured":"Paul Michel, Omer Levy, and Graham Neubig. 2019. Are Sixteen Heads Really Better than One?. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/775"},{"key":"e_1_3_2_1_56_1","volume-title":"An Empirical Comparison of Pre-Trained Models of Source Code. In 45th IEEE\/ACM International Conference on Software Engineering, ICSE 2023","author":"Niu Changan","year":"2023","unstructured":"Changan Niu, Chuanyi Li, Vincent Ng, Dongxiao Chen, Jidong Ge, and Bin Luo. 2023. An Empirical Comparison of Pre-Trained Models of Source Code. In 45th IEEE\/ACM International Conference on Software Engineering, ICSE 2023, Melbourne, Australia, May 14--20, 2023. IEEE, 2136--2148."},{"key":"e_1_3_2_1_57_1","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Niu Liang","year":"2023","unstructured":"Liang Niu, Shujaat Mirza, Zayd Maradni, and Christina P\u00f6pper. 2023. {CodexLeaks}: Privacy Leaks from Code Generation Language Models in {GitHub} Copilot. In 32nd USENIX Security Symposium (USENIX Security 23). 2133--2150."},{"key":"e_1_3_2_1_58_1","volume-title":"Yossi Adi, Jingyu Liu, Tal Remez, J\u00e9r\u00e9my Rapin, et al.","author":"Rozi\u00e8re Baptiste","year":"2023","unstructured":"Baptiste Rozi\u00e8re, 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 preprint arXiv:2308.12950 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_60_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3381831"},{"key":"e_1_3_2_1_62_1","volume-title":"Neural Machine Translation of Rare Words with Subword Units. In 54th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (ACL), 1715--1725","author":"Sennrich Rico","year":"2016","unstructured":"Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Neural Machine Translation of Rare Words with Subword Units. In 54th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (ACL), 1715--1725."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00130"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556964"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3213846.3213852"},{"key":"e_1_3_2_1_67_1","article-title":"Galton, Pearson, and the peas: A brief history of linear regression for statistics instructors","volume":"9","author":"Stanton Jeffrey M","year":"2001","unstructured":"Jeffrey M Stanton. 2001. Galton, Pearson, and the peas: A brief history of linear regression for statistics instructors. Journal of Statistics Education 9, 3 (2001).","journal-title":"Journal of Statistics Education"},{"key":"e_1_3_2_1_68_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Sun Siqi","unstructured":"Siqi Sun, Yu Cheng, Zhe Gan, and Jingjing Liu. 2019. Patient Knowledge Distillation for BERT Model Compression. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 4323--4332."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2014.77"},{"key":"e_1_3_2_1_70_1","volume-title":"Fast and Memory-Efficient Neural Code Completion. In 2021 IEEE\/ACM 18th International Conference on Mining Software Repositories (MSR). 329--340","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 2021 IEEE\/ACM 18th International Conference on Mining Software Repositories (MSR). 329--340."},{"key":"e_1_3_2_1_71_1","volume-title":"Distilling task-specific knowledge from bert into simple neural networks. arXiv preprint arXiv:1903.12136","author":"Tang Raphael","year":"2019","unstructured":"Raphael Tang, Yao Lu, Linqing Liu, Lili Mou, Olga Vechtomova, and Jimmy Lin. 2019. Distilling task-specific knowledge from bert into simple neural networks. arXiv preprint arXiv:1903.12136 (2019)."},{"key":"e_1_3_2_1_72_1","first-page":"211","article-title":"Sparse Bayesian learning and the relevance vector machine","author":"Tipping Michael E","year":"2001","unstructured":"Michael E Tipping. 2001. Sparse Bayesian learning and the relevance vector machine. Journal of machine learning research 1, Jun (2001), 211--244.","journal-title":"Journal of machine learning research 1"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/2975585"},{"key":"e_1_3_2_1_74_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc."},{"key":"e_1_3_2_1_75_1","volume-title":"Parminder Bhatia, and Bing Xiang.","author":"Wei Xiaokai","year":"2023","unstructured":"Xiaokai Wei, Sujan Gonugondla, Shiqi Wang, Wasi Ahmad, Baishakhi Ray, Haifeng Qian, Xiaopeng LI, Varun Kumar, Zijian Wang, Yuchen Tian, Qing Sun, Ben Athiwaratkun, Mingyue Shang, Murali Krishna Ramanathan, Parminder Bhatia, and Bing Xiang. 2023. Towards greener yet powerful code generation via quantization: An empirical study. In ESEC\/FSE 2023."},{"key":"e_1_3_2_1_76_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey et al. 2016. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.633"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467262"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510146"},{"key":"e_1_3_2_1_80_1","volume-title":"What Do Code Models Memorize? An Empirical Study on Large Language Models of Code. arXiv preprint arXiv:2308.09932","author":"Yang Zhou","year":"2023","unstructured":"Zhou Yang, Zhipeng Zhao, Chenyu Wang, Jieke Shi, Dongsun Kim, DongGyun Han, and David Lo. 2023. What Do Code Models Memorize? An Empirical Study on Large Language Models of Code. arXiv preprint arXiv:2308.09932 (2023)."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534390"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549094"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.238"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME52107.2021.00044"},{"key":"e_1_3_2_1_86_1","unstructured":"Yaqin Zhou Shangqing Liu Jingkai Siow Xiaoning Du and Yang Liu. 2019. Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks. In Advances in Neural Information Processing Systems H. Wallach H. Larochelle A. Beygelzimer F. d'Alch\u00e9-Buc E. Fox and R. Garnett (Eds.) Vol. 32. Curran Associates Inc."}],"event":{"name":"ICSE-SEIS'24: 46th International Conference on Software Engineering: Software Engineering in Society","location":"Lisbon Portugal","acronym":"ICSE-SEIS'24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Society"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639475.3640097","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3639475.3640097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:53:38Z","timestamp":1750287218000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639475.3640097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":86,"alternative-id":["10.1145\/3639475.3640097","10.1145\/3639475"],"URL":"https:\/\/doi.org\/10.1145\/3639475.3640097","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]},"assertion":[{"value":"2024-06-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}