{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:41:20Z","timestamp":1783438880465,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","funder":[{"name":"Research Grants Council of the Hong Kong Special Administrative Region, China","award":["SRFS2425-4S03"],"award-info":[{"award-number":["SRFS2425-4S03"]}]},{"name":"CCF-Huawei Populus Grove Fund"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3696630.3728535","type":"proceedings-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:08:09Z","timestamp":1753729689000},"page":"93-104","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3935-7328","authenticated-orcid":false,"given":"Chaozheng","family":"Wang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9092-3381","authenticated-orcid":false,"given":"Zezhou","family":"Yang","sequence":"additional","affiliation":[{"name":"Tencent Inc., Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8102-480X","authenticated-orcid":false,"given":"Shuzheng","family":"Gao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8513-6836","authenticated-orcid":false,"given":"Cuiyun","family":"Gao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6970-0857","authenticated-orcid":false,"given":"Ting","family":"Peng","sequence":"additional","affiliation":[{"name":"Tencent Inc., Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0655-9398","authenticated-orcid":false,"given":"Hailiang","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent Inc., Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7060-4109","authenticated-orcid":false,"given":"Yuetang","family":"Deng","sequence":"additional","affiliation":[{"name":"Tencent Inc., Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3666-5798","authenticated-orcid":false,"given":"Michael","family":"Lyu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Studying LLM Performance on Closed-and Open-source Data. arXiv preprint arXiv:2402.15100","author":"Ahmed Toufique","year":"2024","unstructured":"Toufique Ahmed, Christian Bird, Premkumar Devanbu, and Saikat Chakraborty. 2024. Studying LLM Performance on Closed-and Open-source Data. arXiv preprint arXiv:2402.15100 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, virtual."},{"key":"e_1_3_2_1_3_1","volume-title":"Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174 (2016)."},{"key":"e_1_3_2_1_4_1","unstructured":"ClangD. 2025. ClangD. https:\/\/clangd.llvm.org\/."},{"key":"e_1_3_2_1_5_1","unstructured":"copilot. 2025. copilot. https:\/\/copilot.microsoft.com\/."},{"key":"e_1_3_2_1_6_1","unstructured":"cursor. 2025. cursor. https:\/\/www.cursor.com\/."},{"key":"e_1_3_2_1_7_1","first-page":"16344","article-title":"Flashat-tention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashat-tention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems 35 (2022), 16344\u201316359.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_8_1","first-page":"1536","article-title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","volume":"2020","author":"Feng Zhangyin","year":"2020","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. In Findings of the Association for Computational Linguistics: EMNLP 2020. 1536\u20131547.","journal-title":"Findings of the Association for Computational Linguistics: EMNLP"},{"key":"e_1_3_2_1_9_1","volume-title":"2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE). IEEE Computer Society, 254\u2013266","author":"Gao Shuzheng","year":"2024","unstructured":"Shuzheng Gao, Cuiyun Gao, Wenchao Gu, and Michael Lyu. 2024. Search-based llms for code optimization. In 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE). IEEE Computer Society, 254\u2013266."},{"key":"e_1_3_2_1_10_1","article-title":"Code Structure-Guided Transformer for Source Code Summarization","volume":"32","author":"Gao Shuzheng","year":"2023","unstructured":"Shuzheng Gao, Cuiyun Gao, Yulan He, Jichuan Zeng, Lunyiu Nie, Xin Xia, and Michael R. Lyu. 2023. Code Structure-Guided Transformer for Source Code Summarization. ACM Trans. Softw. Eng. Methodol. 32, 1 (2023), 23:1\u201323:32.","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering, ICSE 2024","author":"Gao Shuzheng","year":"2024","unstructured":"Shuzheng Gao, Wenxin Mao, Cuiyun Gao, Li Li, Xing Hu, Xin Xia, and Michael R. Lyu. 2024. Learning in the Wild: Towards Leveraging Unlabeled Data for Effectively Tuning Pre-trained Code Models. In Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering, ICSE 2024, Lisbon, Portugal, April 14\u201320, 2024. ACM, 80:1\u201380:13."},{"key":"e_1_3_2_1_12_1","volume-title":"2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 761\u2013773","author":"Gao Shuzheng","year":"2023","unstructured":"Shuzheng Gao, Xin-Cheng Wen, Cuiyun Gao, Wenxuan Wang, Hongyu Zhang, and Michael R Lyu. 2023. What makes good in-context demonstrations for code intelligence tasks with llms?. In 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 761\u2013773."},{"key":"e_1_3_2_1_13_1","volume-title":"Keeping Pace with Ever-Increasing Data: Towards Continual Learning of Code Intelligence Models. In 45th IEEE\/ACM International Conference on Software Engineering, ICSE 2023","author":"Gao Shuzheng","year":"2023","unstructured":"Shuzheng Gao, Hongyu Zhang, Cuiyun Gao, and Chaozheng Wang. 2023. Keeping Pace with Ever-Increasing Data: Towards Continual Learning of Code Intelligence Models. In 45th IEEE\/ACM International Conference on Software Engineering, ICSE 2023, Melbourne, Australia, May 14\u201320, 2023. IEEE, 30\u201342."},{"key":"e_1_3_2_1_14_1","volume-title":"Understanding and Execution. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Gu Alex","year":"2024","unstructured":"Alex Gu, Baptiste Rozi\u00e8re, Hugh James Leather, Armando Solar-Lezama, Gabriel Synnaeve, and Sida Wang. 2024. CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21\u201327, 2024. OpenReview.net."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 7212\u20137225","author":"Guo Daya","year":"2022","unstructured":"Daya Guo, Shuai Lu, Nan Duan, Yanlin Wang, Ming Zhou, and Jian Yin. 2022. UniXcoder: Unified Cross-Modal Pre-training for Code Representation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 7212\u20137225."},{"key":"e_1_3_2_1_16_1","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Y Wu YK Li et al. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming-The Rise of Code Intelligence. arXiv preprint arXiv:2401.14196 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Distilling the Knowledge in a Neural Network. CoRR abs\/1503.02531","author":"Hinton Geoffrey E.","year":"2015","unstructured":"Geoffrey E. Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. CoRR abs\/1503.02531 (2015)."},{"key":"e_1_3_2_1_18_1","unstructured":"Binyuan Hui Jian Yang Zeyu Cui Jiaxi Yang Dayiheng Liu Lei Zhang Tianyu Liu Jiajun Zhang Bowen Yu Keming Lu et al. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Decoupled Weight Decay Regularization. International Conference on Learning Representations, ICLR","author":"Ilya Loshchilov","year":"2018","unstructured":"Loshchilov Ilya and Hutter Frank. 2018. Decoupled Weight Decay Regularization. International Conference on Learning Representations, ICLR (2018)."},{"key":"e_1_3_2_1_20_1","volume-title":"44th IEEE\/ACM 44th International Conference on Software Engineering, ICSE 2022","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 44th IEEE\/ACM 44th International Conference on Software Engineering, ICSE 2022, Pittsburgh, PA, USA, May 25\u201327, 2022. ACM, 401\u2013412."},{"key":"e_1_3_2_1_21_1","volume-title":"Benchmarking and explaining large language model-based code generation: A causality-centric approach. arXiv preprint arXiv:2310.06680","author":"Ji Zhenlan","year":"2023","unstructured":"Zhenlan Ji, Pingchuan Ma, Zongjie Li, and Shuai Wang. 2023. Benchmarking and explaining large language model-based code generation: A causality-centric approach. arXiv preprint arXiv:2310.06680 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs. arXiv preprint arXiv:2404.17833","author":"Ji Zhenlan","year":"2024","unstructured":"Zhenlan Ji, Daoyuan Wu, Pingchuan Ma, Zongjie Li, and Shuai Wang. 2024. Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs. arXiv preprint arXiv:2404.17833 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Efficient Deep Learning Inference on Edge Devices. MLsys","author":"Jiang Ziheng","year":"2018","unstructured":"Ziheng Jiang, Tianqi Chen, and Mu Li. 2018. Efficient Deep Learning Inference on Edge Devices. MLsys (2018)."},{"key":"e_1_3_2_1_24_1","volume-title":"Generalization through memorization: Nearest neighbor language models. arXiv preprint arXiv:1911.00172","author":"Khandelwal Urvashi","year":"2019","unstructured":"Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2019. Generalization through memorization: Nearest neighbor language models. arXiv preprint arXiv:1911.00172 (2019)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the national academy of sciences 114","author":"Kirkpatrick James","year":"2017","unstructured":"James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al. 2017. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences 114, 13 (2017), 3521\u20133526."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 29th Symposium on Operating Systems Principles. 611\u2013626","author":"Kwon Woosuk","year":"2023","unstructured":"Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the 29th Symposium on Operating Systems Principles. 611\u2013626."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2024","author":"Li Guochang","year":"2024","unstructured":"Guochang Li, Chen Zhi, Jialiang Chen, Junxiao Han, and Shuiguang Deng. 2024. Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair. In Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2024, Sacramento, CA, USA, October 27 - November 1, 2024. ACM, 719\u2013731."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018","author":"Li Jian","year":"2018","unstructured":"Jian Li, Yue Wang, Michael R. Lyu, and Irwin King. 2018. Code Completion with Neural Attention and Pointer Networks. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, July 13\u201319, 2018, Stockholm, Sweden. ijcai.org, 4159\u20134165."},{"key":"e_1_3_2_1_29_1","volume-title":"44th IEEE\/ACM 44th International Conference on Software Engineering, ICSE 2022","author":"Li Zongjie","year":"2022","unstructured":"Zongjie Li, Pingchuan Ma, Huaijin Wang, Shuai Wang, Qiyi Tang, Sen Nie, and Shi Wu. 2022. Unleashing the Power of Compiler Intermediate Representation to Enhance Neural Program Embeddings. In 44th IEEE\/ACM 44th International Conference on Software Engineering, ICSE 2022, Pittsburgh, PA, USA, May 25\u201327, 2022. ACM."},{"key":"e_1_3_2_1_30_1","volume-title":"CCTEST: Testing and Repairing Code Completion Systems. In 45th IEEE\/ACM International Conference on Software Engineering, ICSE 2023","author":"Li Zongjie","year":"2023","unstructured":"Zongjie Li, Chaozheng Wang, Zhibo Liu, Haoxuan Wang, Dong Chen, Shuai Wang, and Cuiyun Gao. 2023. CCTEST: Testing and Repairing Code Completion Systems. In 45th IEEE\/ACM International Conference on Software Engineering, ICSE 2023, Melbourne, Australia, May 14\u201320, 2023. IEEE, 1238\u20131250."},{"key":"e_1_3_2_1_31_1","volume-title":"CCTEST: Testing and Repairing Code Completion Systems. In 45th IEEE\/ACM International Conference on Software Engineering, ICSE 2023","author":"Li Zongjie","year":"2023","unstructured":"Zongjie Li, Chaozheng Wang, Zhibo Liu, Haoxuan Wang, Dong Chen, Shuai Wang, and Cuiyun Gao. 2023. CCTEST: Testing and Repairing Code Completion Systems. In 45th IEEE\/ACM International Conference on Software Engineering, ICSE 2023, Melbourne, Australia, May 14\u201320, 2023. IEEE, 1238\u20131250."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering","author":"Li Zongjie","year":"2024","unstructured":"Zongjie Li, Chaozheng Wang, Pingchuan Ma, Chaowei Liu, Shuai Wang, Daoyuan Wu, Cuiyun Gao, and Yang Liu. 2024. On Extracting Specialized Code Abilities from Large Language Models: A Feasibility Study. In Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering (Lisbon, Portugal) (ICSE '24). Association for Computing Machinery, New York, NY, USA, Article 74, 13 pages."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, CCS 2023","author":"Li Zongjie","year":"2023","unstructured":"Zongjie Li, Chaozheng Wang, Shuai Wang, and Gao Cuiyun. 2023. Protecting Intellectual Property of Large Language Model-Based Code Generation APIs via Watermarks. In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, CCS 2023, Copenhagen, Denmark, November 26\u201330, 2023."},{"key":"e_1_3_2_1_34_1","volume-title":"API-guided Dataset Synthesis to Finetune Large Code Models. arXiv preprint arXiv:2408.08343","author":"Li Zongjie","year":"2024","unstructured":"Zongjie Li, Daoyuan Wu, Shuai Wang, and Zhendong Su. 2024. API-guided Dataset Synthesis to Finetune Large Code Models. arXiv preprint arXiv:2408.08343 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Liu Tianyang","year":"2024","unstructured":"Tianyang Liu, Canwen Xu, and Julian J. McAuley. 2024. RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7\u201311, 2024. OpenReview.net."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2024","author":"Liu Wei","year":"2024","unstructured":"Wei Liu, Ailun Yu, Daoguang Zan, Bo Shen, Wei Zhang, Haiyan Zhao, Zhi Jin, and Qianxiang Wang. 2024. GraphCoder: Enhancing Repository-Level Code Completion via Coarse-to-fine Retrieval Based on Code Context Graph. In Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2024, Sacramento, CA, USA, October 27 - November 1, 2024. ACM, 570\u2013581."},{"key":"e_1_3_2_1_37_1","volume-title":"SGDR: Stochastic Gradient Descent with Warm Restarts. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. SGDR: Stochastic Gradient Descent with Warm Restarts. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022","author":"Lu Shuai","year":"2022","unstructured":"Shuai Lu, Nan Duan, Hojae Han, Daya Guo, Seung-won Hwang, and Alexey Svyatkovskiy. 2022. ReACC: A Retrieval-Augmented Code Completion Framework. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22\u201327, 2022. Association for Computational Linguistics, 6227\u20136240."},{"key":"e_1_3_2_1_39_1","series-title":"Round 1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Lu Shuai","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, Duyu Tang, et al. [n. d.]. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)."},{"key":"e_1_3_2_1_40_1","volume-title":"Shengyu Fu, and Shujie Liu.","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, 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. (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Bm25s: Orders of magnitude faster lexical search via eager sparse scoring. arXiv preprint arXiv:2407.03618","author":"Xing Han L\u00f9.","year":"2024","unstructured":"Xing Han L\u00f9. 2024. Bm25s: Orders of magnitude faster lexical search via eager sparse scoring. arXiv preprint arXiv:2407.03618 (2024)."},{"key":"e_1_3_2_1_42_1","volume-title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Luo Ziyang","year":"2024","unstructured":"Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, Qingwei Lin, and Daxin Jiang. 2024. WizardCoder: Empowering Code Large Language Models with Evol-Instruct. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7\u201311, 2024. OpenReview.net."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3722554"},{"key":"e_1_3_2_1_44_1","volume-title":"Psychology of learning and motivation.","author":"McCloskey Michael","unstructured":"Michael McCloskey and Neal J Cohen. 1989. Catastrophic interference in connectionist networks: The sequential learning problem. In Psychology of learning and motivation. Vol. 24. Elsevier, 109\u2013165."},{"key":"e_1_3_2_1_45_1","volume-title":"Contextual API Completion for Unseen Repositories Using LLMs. arXiv preprint arXiv:2405.04600","author":"Nashid Noor","year":"2024","unstructured":"Noor Nashid, Taha Shabani, Parsa Alian, and Ali Mesbah. 2024. Contextual API Completion for Unseen Repositories Using LLMs. arXiv preprint arXiv:2405.04600 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, July 6\u201312","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 of the Association for Computational Linguistics, July 6\u201312, 2002, Philadelphia, PA, USA. ACL, 311\u2013318."},{"key":"e_1_3_2_1_47_1","volume-title":"Retrieval Augmented Code Generation and Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2021","author":"Rizwan Parvez Md.","year":"2021","unstructured":"Md. Rizwan Parvez, Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang. 2021. Retrieval Augmented Code Generation and Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event \/ Punta Cana, Dominican Republic, 16\u201320 November, 2021. Association for Computational Linguistics, 2719\u20132734."},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering, ICSE 2024","author":"Peng Yun","year":"2024","unstructured":"Yun Peng, Shuzheng Gao, Cuiyun Gao, Yintong Huo, and Michael R. Lyu. 2024. Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors. In Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering, ICSE 2024, Lisbon, Portugal, April 14\u201320, 2024. ACM, 4:1\u20134:13."},{"key":"e_1_3_2_1_49_1","first-page":"23","article-title":"An empirical comparison of c, c++, java, perl, python, rexx and tcl","volume":"33","author":"Prechelt Lutz","year":"2000","unstructured":"Lutz Prechelt. 2000. An empirical comparison of c, c++, java, perl, python, rexx and tcl. IEEE Computer 33, 10 (2000), 23\u201329.","journal-title":"IEEE Computer"},{"key":"e_1_3_2_1_50_1","unstructured":"qdrant. 2025. qdrant. https:\/\/qdrant.tech\/\/."},{"key":"e_1_3_2_1_51_1","volume-title":"Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:2009.10297","author":"Ren Shuo","year":"2020","unstructured":"Shuo Ren, Daya Guo, Shuai Lu, Long Zhou, Shujie Liu, Duyu Tang, Neel Sundaresan, Ming Zhou, Ambrosio Blanco, and Shuai Ma. 2020. Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:2009.10297 (2020)."},{"key":"e_1_3_2_1_52_1","volume-title":"2022 IEEE High Performance Extreme Computing Conference (HPEC). IEEE, 1\u201310","author":"Reuther Albert","year":"2022","unstructured":"Albert Reuther, Peter Michaleas, Michael Jones, Vijay Gadepally, Siddharth Samsi, and Jeremy Kepner. 2022. AI and ML accelerator survey and trends. In 2022 IEEE High Performance Extreme Computing Conference (HPEC). IEEE, 1\u201310."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Stephen Robertson Hugo Zaragoza et al. 2009. The probabilistic relevance framework: BM25 and beyond. Foundations and Trends\u00ae in Information Retrieval 3 4 (2009) 333\u2013389.","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_54_1","volume-title":"Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al.","author":"Roziere Baptiste","year":"2023","unstructured":"Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)."},{"key":"e_1_3_2_1_55_1","volume-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 2198\u20132210","author":"Shi Ensheng","year":"2023","unstructured":"Ensheng Shi, Yanlin Wang, Wenchao Gu, Lun Du, Hongyu Zhang, Shi Han, Dongmei Zhang, and Hongbin Sun. 2023. Cocosoda: Effective contrastive learning for code search. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 2198\u20132210."},{"key":"e_1_3_2_1_56_1","volume-title":"2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 421\u2013433","author":"Tang Ze","year":"2023","unstructured":"Ze Tang, Jidong Ge, Shangqing Liu, Tingwei Zhu, Tongtong Xu, Liguo Huang, and Bin Luo. 2023. Domain adaptive code completion via language models and decoupled domain databases. In 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 421\u2013433."},{"key":"e_1_3_2_1_57_1","unstructured":"tantivy. 2025. tantivy. https:\/\/github.com\/quickwit-oss\/tantivy."},{"key":"e_1_3_2_1_58_1","unstructured":"tree sitter. 2025. tree-sitter. https:\/\/tree-sitter.github.io\/tree-sitter\/."},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2024","author":"Wang Chaozheng","year":"2024","unstructured":"Chaozheng Wang, Shuzheng Gao, Cuiyun Gao, Wenxuan Wang, Chun Yong Chong, Shan Gao, and Michael R. Lyu. 2024. A Systematic Evaluation of Large Code Models in API Suggestion: When, Which, and How. In Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2024, Sacramento, CA, USA, October 27 - November 1, 2024. ACM, 281\u2013293."},{"key":"e_1_3_2_1_60_1","volume-title":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC\/FSE 2023","author":"Wang Chaozheng","year":"2023","unstructured":"Chaozheng Wang, Junhao Hu, Cuiyun Gao, Yu Jin, Tao Xie, Hailiang Huang, Zhenyu Lei, and Yuetang Deng. 2023. How Practitioners Expect Code Completion?. In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC\/FSE 2023, San Francisco, CA, USA, December 3\u20139, 2023. ACM, 1294\u20131306."},{"key":"e_1_3_2_1_61_1","volume-title":"Exploring Multi-Lingual Bias of Large Code Models in Code Generation. arXiv preprint arXiv:2404.19368","author":"Wang Chaozheng","year":"2024","unstructured":"Chaozheng Wang, Zongjie Li, Cuiyun Gao, Wenxuan Wang, Ting Peng, Hailiang Huang, Yuetang Deng, Shuai Wang, and Michael R Lyu. 2024. Exploring Multi-Lingual Bias of Large Code Models in Code Generation. arXiv preprint arXiv:2404.19368 (2024)."},{"key":"e_1_3_2_1_62_1","volume-title":"REEF: A Framework for Collecting Real-World Vulnerabilities and Fixes. In 38th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2023","author":"Wang Chaozheng","year":"2023","unstructured":"Chaozheng Wang, Zongjie Li, Yun Peng, Shuzheng Gao, Sirong Chen, Shuai Wang, Cuiyun Gao, and Michael R. Lyu. 2023. REEF: A Framework for Collecting Real-World Vulnerabilities and Fixes. In 38th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2023, Luxembourg, September 11\u201315, 2023. IEEE, 1952\u20131962."},{"key":"e_1_3_2_1_63_1","volume-title":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC\/FSE 2022","author":"Wang Chaozheng","year":"2022","unstructured":"Chaozheng Wang, Yuanhang Yang, Cuiyun Gao, Yun Peng, Hongyu Zhang, and Michael R. Lyu. [n. d.]. No more fine-tuning? an experimental evaluation of prompt tuning in code intelligence. In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC\/FSE 2022, Singapore, Singapore, November 14\u201318, 2022. 382\u2013394."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"crossref","first-page":"4869","DOI":"10.1109\/TSE.2023.3313881","article-title":"Prompt Tuning in Code Intelligence","volume":"49","author":"Wang Chaozheng","year":"2023","unstructured":"Chaozheng Wang, Yuanhang Yang, Cuiyun Gao, Yun Peng, Hongyu Zhang, and Michael R. Lyu. 2023. Prompt Tuning in Code Intelligence: An Experimental Evaluation. IEEE Trans. Software Eng. 49, 11 (2023), 4869\u20134885.","journal-title":"An Experimental Evaluation. IEEE Trans. Software Eng."},{"key":"e_1_3_2_1_65_1","volume-title":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC\/FSE 2023","author":"Wang Weishi","year":"2023","unstructured":"Weishi Wang, Yue Wang, Shafiq Joty, and Steven C. H. Hoi. 2023. RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair. In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC\/FSE 2023, San Francisco, CA, USA, December 3\u20139, 2023. ACM, 146\u2013158."},{"key":"e_1_3_2_1_66_1","volume-title":"RLCoder: Reinforcement Learning for Repository-Level Code Completion. CoRR abs\/2407.19487","author":"Wang Yanlin","year":"2024","unstructured":"Yanlin Wang, Daya Guo, Jiachi Chen, Ruikai Zhang, Yuchi Ma, and Zibin Zheng. 2024. RLCoder: Reinforcement Learning for Repository-Level Code Completion. CoRR abs\/2407.19487 (2024)."},{"key":"e_1_3_2_1_67_1","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 8696\u20138708","author":"Wang Yue","year":"2021","unstructured":"Yue Wang, Weishi Wang, Shafiq Joty, and Steven CH Hoi. 2021. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 8696\u20138708."},{"key":"e_1_3_2_1_68_1","volume-title":"Magicoder: Empowering Code Generation with OSS-Instruct. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Wei Yuxiang","year":"2024","unstructured":"Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, and Lingming Zhang. 2024. Magicoder: Empowering Code Generation with OSS-Instruct. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21\u201327, 2024. OpenReview.net."},{"key":"e_1_3_2_1_69_1","volume-title":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2024","author":"Wen Xin-Cheng","year":"2024","unstructured":"Xin-Cheng Wen, Cuiyun Gao, Shuzheng Gao, Yang Xiao, and Michael R. Lyu. 2024. SCALE: Constructing Structured Natural Language Comment Trees for Software Vulnerability Detection. In Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2024, Vienna, Austria, September 16\u201320, 2024. ACM, 235\u2013247."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1002\/(SICI)1097-024X(19980425)28:5<513::AID-SPE165>3.0.CO;2-H","article-title":"Measuring complexity in C++ application software. Software","volume":"28","author":"George Wilkie F","year":"1998","unstructured":"F George Wilkie and B Hylands. 1998. Measuring complexity in C++ application software. Software: Practice and Experience 28, 5 (1998), 513\u2013546.","journal-title":"Practice and Experience"},{"key":"e_1_3_2_1_71_1","volume-title":"Refining decompiled c code with large language models. arXiv preprint arXiv:2310.06530","author":"Wong Wai Kin","year":"2023","unstructured":"Wai Kin Wong, Huaijin Wang, Zongjie Li, Zhibo Liu, Shuai Wang, Qiyi Tang, Sen Nie, and Shi Wu. 2023. Refining decompiled c code with large language models. arXiv preprint arXiv:2310.06530 (2023)."},{"key":"e_1_3_2_1_72_1","volume-title":"Chatqa 2: Bridging the gap to proprietary llms in long context and rag capabilities. arXiv preprint arXiv:2407.14482","author":"Xu Peng","year":"2024","unstructured":"Peng Xu, Wei Ping, Xianchao Wu, Chejian Xu, Zihan Liu, Mohammad Shoeybi, and Bryan Catanzaro. 2024. Chatqa 2: Bridging the gap to proprietary llms in long context and rag capabilities. arXiv preprint arXiv:2407.14482 (2024)."},{"key":"e_1_3_2_1_73_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 Technical Report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_74_1","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023","author":"Zhang Fengji","year":"2023","unstructured":"Fengji Zhang, Bei Chen, Yue Zhang, Jacky Keung, Jin Liu, Daoguang Zan, Yi Mao, Jian-Guang Lou, and Weizhu Chen. 2023. RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6\u201310, 2023. Association for Computational Linguistics, 2471\u20132484."},{"key":"e_1_3_2_1_75_1","volume-title":"ICSE '20: 42nd International Conference on Software Engineering","author":"Zhang Jian","year":"2020","unstructured":"Jian Zhang, Xu Wang, Hongyu Zhang, Hailong Sun, and Xudong Liu. 2020. Retrieval-based neural source code summarization. In ICSE '20: 42nd International Conference on Software Engineering, Seoul, South Korea, 27 June - 19 July, 2020. ACM, 1385\u20131397."},{"key":"e_1_3_2_1_76_1","volume-title":"Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators. arXiv preprint arXiv:2501.19282","author":"Zhang Kunpeng","year":"2025","unstructured":"Kunpeng Zhang, Zongjie Li, Daoyuan Wu, Shuai Wang, and Xin Xia. 2025. Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators. arXiv preprint arXiv:2501.19282 (2025)."}],"event":{"name":"FSE Companion '25: 33rd ACM International Conference on the Foundations of Software Engineering","location":"Clarion Hotel Trondheim Trondheim Norway","acronym":"FSE Companion '25","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696630.3728535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:13:29Z","timestamp":1753730009000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696630.3728535"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":76,"alternative-id":["10.1145\/3696630.3728535","10.1145\/3696630"],"URL":"https:\/\/doi.org\/10.1145\/3696630.3728535","relation":{},"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"2025-07-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}