{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T23:15:59Z","timestamp":1776122159810,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T00:00:00Z","timestamp":1721779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,24]]},"DOI":"10.1145\/3671016.3674819","type":"proceedings-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T20:19:32Z","timestamp":1721247572000},"page":"229-238","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["RepoMinCoder: Improving Repository-Level Code Generation Based on Information Loss Screening"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2679-8853","authenticated-orcid":false,"given":"Yifan","family":"Li","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5543-2025","authenticated-orcid":false,"given":"Ensheng","family":"Shi","sequence":"additional","affiliation":[{"name":"Xi?an Jiaotong University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5276-5325","authenticated-orcid":false,"given":"Dewu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4465-3600","authenticated-orcid":false,"given":"Kefeng","family":"Duan","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0192-9992","authenticated-orcid":false,"given":"Jiachi","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7761-7269","authenticated-orcid":false,"given":"Yanlin","family":"Wang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, China"}]}],"member":"320","published-online":{"date-parts":[[2024,7,24]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00065"},{"key":"e_1_3_2_1_2_1","volume-title":"CodePlan: Repository-level Coding using LLMs and Planning. ArXiv abs\/2309.12499","author":"Bairi Ramakrishna","year":"2023","unstructured":"Ramakrishna Bairi, Atharv Sonwane, Aditya Kanade, C VageeshD, Arun\u00a0Shankar Iyer, Suresh Parthasarathy, Sriram\u00a0K. Rajamani, B. Ashok, and Shashank\u00a0P. Shet. 2023. CodePlan: Repository-level Coding using LLMs and Planning. ArXiv abs\/2309.12499 (2023). https:\/\/api.semanticscholar.org\/CorpusID:262217135"},{"key":"e_1_3_2_1_3_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique\u00a0Ponde de Oliveira\u00a0Pinto and et al.2021. Evaluating Large Language Models Trained on Code. arxiv:2107.03374\u00a0[cs.LG]"},{"key":"e_1_3_2_1_4_1","volume-title":"CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context. ArXiv abs\/2212.10007","author":"Ding Yangruibo","year":"2022","unstructured":"Yangruibo Ding, Zijian Wang, Wasi\u00a0Uddin Ahmad, Murali\u00a0Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang. 2022. CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context. ArXiv abs\/2212.10007 (2022). https:\/\/api.semanticscholar.org\/CorpusID:254877371"},{"key":"e_1_3_2_1_5_1","unstructured":"Qingxiu Dong Lei Li Damai Dai Ce Zheng Zhiyong Wu Baobao Chang Xu Sun Jingjing Xu and Zhifang Sui. 2022. A Survey on In-context Learning. https:\/\/api.semanticscholar.org\/CorpusID:255372865"},{"key":"e_1_3_2_1_6_1","volume-title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages. ArXiv abs\/2002.08155","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, and Ming Zhou. 2020. CodeBERT: A Pre-Trained Model for Programming and Natural Languages. ArXiv abs\/2002.08155 (2020). https:\/\/api.semanticscholar.org\/CorpusID:211171605"},{"key":"e_1_3_2_1_7_1","volume-title":"Luke Zettlemoyer, and Mike Lewis.","author":"Fried Daniel","year":"2022","unstructured":"Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida\u00a0I. Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen tau Yih, Luke Zettlemoyer, and Mike Lewis. 2022. InCoder: A Generative Model for Code Infilling and Synthesis. ArXiv abs\/2204.05999 (2022). https:\/\/api.semanticscholar.org\/CorpusID:248157108"},{"key":"e_1_3_2_1_8_1","volume-title":"Gr\u00fcnwald and Teemu Roos","author":"D.","year":"2019","unstructured":"Peter\u00a0D. Gr\u00fcnwald and Teemu Roos. 2019. Minimum Description Length Revisited. ArXiv abs\/1908.08484 (2019). https:\/\/api.semanticscholar.org\/CorpusID:201314867"},{"key":"e_1_3_2_1_9_1","volume-title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:247315559","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 Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:247315559"},{"key":"e_1_3_2_1_10_1","volume-title":"Coverage-based Example Selection for In-Context Learning. ArXiv abs\/2305.14907","author":"Gupta Shivanshu","year":"2023","unstructured":"Shivanshu Gupta, Sameer Singh, and Matt Gardner. 2023. Coverage-based Example Selection for In-Context Learning. ArXiv abs\/2305.14907 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258865631"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00101"},{"key":"e_1_3_2_1_12_1","unstructured":"Samuel Humeau Kurt Shuster Marie-Anne Lachaux and Jason Weston. 2019. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:210063976"},{"key":"e_1_3_2_1_13_1","volume-title":"Few-shot Learning with Retrieval Augmented Language Models. ArXiv abs\/2208.03299","author":"Izacard Gautier","year":"2022","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane\u00a0A. Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2022. Few-shot Learning with Retrieval Augmented Language Models. ArXiv abs\/2208.03299 (2022). https:\/\/api.semanticscholar.org\/CorpusID:251371732"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-8137.1912.tb05611.x"},{"key":"e_1_3_2_1_15_1","volume-title":"Self-planning Code Generation with Large Language Model. ArXiv abs\/2303.06689","author":"Jiang Xue","year":"2023","unstructured":"Xue Jiang, Yihong Dong, Lecheng Wang, Qiwei Shang, and Ge Li. 2023. Self-planning Code Generation with Large Language Model. ArXiv abs\/2303.06689 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257495755"},{"key":"e_1_3_2_1_16_1","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals. Soviet physics","volume":"10","author":"Levenshtein I.","year":"1965","unstructured":"Vladimir\u00a0I. Levenshtein. 1965. Binary codes capable of correcting deletions, insertions, and reversals. Soviet physics. Doklady 10 (1965), 707\u2013710. https:\/\/api.semanticscholar.org\/CorpusID:60827152","journal-title":"Doklady"},{"key":"e_1_3_2_1_17_1","unstructured":"Jia Li Ge Li Yongming Li and Zhi Jin. 2023. Structured Chain-of-Thought Prompting for Code Generation. https:\/\/api.semanticscholar.org\/CorpusID:258615421"},{"key":"e_1_3_2_1_18_1","unstructured":"Jia Li Yunfei Zhao Yongming Li Ge Li and Zhi Jin. 2023. AceCoder: Utilizing Existing Code to Enhance Code Generation. https:\/\/api.semanticscholar.org\/CorpusID:257901190"},{"key":"e_1_3_2_1_19_1","volume-title":"Starcoder: may the source be with you!arXiv preprint arXiv:2305.06161","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna\u00a0Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, 2023. Starcoder: may the source be with you!arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_3_2_1_20_1","unstructured":"Dianshu Liao Shidong Pan Xiaoyu Sun Xiaoxue Ren Qing Huang Zhenchang Xing Huan Jin and Qinying Li. 2023. A-CodGen: A Repository-Level Code Generation Framework for Code Reuse with Local-Aware Global-Aware and Third-Party-Library-Aware. https:\/\/api.semanticscholar.org\/CorpusID:266162660"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00159"},{"key":"e_1_3_2_1_22_1","volume-title":"Compositional API Recommendation for Library-Oriented Code Generation. ArXiv abs\/2402.19431","author":"Ma Zexiong","year":"2024","unstructured":"Zexiong Ma, Shengnan An, Bing Xie, and Zeqi Lin. 2024. Compositional API Recommendation for Library-Oriented Code Generation. ArXiv abs\/2402.19431 (2024). https:\/\/api.semanticscholar.org\/CorpusID:268091217"},{"key":"e_1_3_2_1_23_1","volume-title":"CodeGen2: Lessons for Training LLMs on Programming and Natural Languages. ICLR","author":"Nijkamp Erik","year":"2023","unstructured":"Erik Nijkamp, Hiroaki Hayashi, Caiming Xiong, Silvio Savarese, and Yingbo Zhou. 2023. CodeGen2: Lessons for Training LLMs on Programming and Natural Languages. ICLR (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:252668917","author":"Nijkamp Erik","year":"2022","unstructured":"Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Haiquan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. 2022. CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:252668917"},{"key":"e_1_3_2_1_25_1","volume-title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. ICLR","author":"Nijkamp Erik","year":"2023","unstructured":"Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. 2023. CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. ICLR (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Retrieval Augmented Code Generation and Summarization. ArXiv abs\/2108.11601","author":"Parvez Rizwan","year":"2021","unstructured":"Md.\u00a0Rizwan Parvez, Wasi\u00a0Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang. 2021. Retrieval Augmented Code Generation and Summarization. ArXiv abs\/2108.11601 (2021). https:\/\/api.semanticscholar.org\/CorpusID:237304122"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00605"},{"key":"e_1_3_2_1_28_1","volume-title":"Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950","author":"Roziere Baptiste","year":"2023","unstructured":"Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing\u00a0Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, J\u00e9r\u00e9my Rapin, 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Repository-Level Prompt Generation for Large Language Models of Code. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:250072448","author":"Shrivastava Disha","year":"2022","unstructured":"Disha Shrivastava, H. Larochelle, and Daniel Tarlow. 2022. Repository-Level Prompt Generation for Large Language Models of Code. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:250072448"},{"key":"e_1_3_2_1_30_1","volume-title":"Lamda: Language models for dialog applications. arXiv preprint arXiv:2201.08239","author":"Thoppilan Romal","year":"2022","unstructured":"Romal Thoppilan, Daniel De\u00a0Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, 2022. Lamda: Language models for dialog applications. arXiv preprint arXiv:2201.08239 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"J. Wang Chengyu Wang Chuanqi Tan Jun Huang and Ming Gao. 2023. Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning. https:\/\/api.semanticscholar.org\/CorpusID:262827483","DOI":"10.18653\/v1\/2024.findings-naacl.207"},{"key":"e_1_3_2_1_32_1","volume-title":"\u00a0H. Hoi","author":"Wang Yue","year":"2021","unstructured":"Yue Wang, Weishi Wang, Shafiq\u00a0R. Joty, and Steven C.\u00a0H. Hoi. 2021. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation. ArXiv abs\/2109.00859 (2021). https:\/\/api.semanticscholar.org\/CorpusID:237386541"},{"key":"e_1_3_2_1_33_1","volume-title":"Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing. ArXiv abs\/2305.18584","author":"Wei Jiayi","year":"2023","unstructured":"Jiayi Wei, Greg Durrett, and I\u015f\u0131l Dillig. 2023. Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing. ArXiv abs\/2305.18584 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258967769"},{"key":"e_1_3_2_1_34_1","volume-title":"F. Xia, Quoc Le, and Denny Zhou.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed\u00a0Huai hsin Chi, F. Xia, Quoc Le, and Denny Zhou. 2022. Chain of Thought Prompting Elicits Reasoning in Large Language Models. ArXiv abs\/2201.11903 (2022). https:\/\/api.semanticscholar.org\/CorpusID:246411621"},{"key":"e_1_3_2_1_35_1","volume-title":"Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models. ArXiv abs\/2308.10462","author":"Weyssow Martin","year":"2023","unstructured":"Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, and Houari\u00a0A. Sahraoui. 2023. Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models. ArXiv abs\/2308.10462 (2023). https:\/\/api.semanticscholar.org\/CorpusID:261048999"},{"key":"e_1_3_2_1_36_1","volume-title":"Repoformer: Selective Retrieval for Repository-Level Code Completion. ArXiv abs\/2403.10059","author":"Wu Di","year":"2024","unstructured":"Di Wu, Wasi\u00a0Uddin Ahmad, Dejiao Zhang, Murali\u00a0Krishna Ramanathan, and Xiaofei Ma. 2024. Repoformer: Selective Retrieval for Repository-Level Code Completion. ArXiv abs\/2403.10059 (2024). https:\/\/api.semanticscholar.org\/CorpusID:268509840"},{"key":"e_1_3_2_1_37_1","unstructured":"Zhiyong Wu Yaoxiang Wang Jiacheng Ye and Lingpeng Kong. 2022. Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:254877590"},{"key":"e_1_3_2_1_38_1","volume-title":"Private-Library-Oriented Code Generation with Large Language Models. ArXiv abs\/2307.15370","author":"Zan Daoguang","year":"2023","unstructured":"Daoguang Zan, B. Chen, Yongshun Gong, Junzhi Cao, Fengji Zhang, Bingchao Wu, Bei Guan, Yilong Yin, and Yongji Wang. 2023. Private-Library-Oriented Code Generation with Large Language Models. ArXiv abs\/2307.15370 (2023). https:\/\/api.semanticscholar.org\/CorpusID:260316265"},{"key":"e_1_3_2_1_39_1","volume-title":"When Language Model Meets Private Library. In Conference on Empirical Methods in Natural Language Processing. https:\/\/api.semanticscholar.org\/CorpusID:253237115","author":"Zan Daoguang","year":"2022","unstructured":"Daoguang Zan, Bei Chen, Zeqi Lin, Bei Guan, Yongji Wang, and Jian-Guang Lou. 2022. When Language Model Meets Private Library. In Conference on Empirical Methods in Natural Language Processing. https:\/\/api.semanticscholar.org\/CorpusID:253237115"},{"key":"e_1_3_2_1_40_1","volume-title":"International Conference on Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:252596262","author":"Zemlyanskiy Yury","year":"2022","unstructured":"Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie, Panupong Pasupat, Peter Shaw, Linlu Qiu, Sumit\u00a0K. Sanghai, and Fei Sha. 2022. Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing. In International Conference on Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:252596262"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Fengji Zhang B. 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. In Conference on Empirical Methods in Natural Language Processing. https:\/\/api.semanticscholar.org\/CorpusID:257663528","DOI":"10.18653\/v1\/2023.emnlp-main.151"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549094"},{"key":"e_1_3_2_1_43_1","volume-title":"International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:252734952","author":"Zhou Shuyan","year":"2022","unstructured":"Shuyan Zhou, Uri Alon, Frank\u00a0F. Xu, Zhiruo Wang, Zhengbao Jiang, and Graham Neubig. 2022. DocPrompting: Generating Code by Retrieving the Docs. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:252734952"}],"event":{"name":"Internetware 2024: 15th Asia-Pacific Symposium on Internetware","location":"Macau China","acronym":"Internetware 2024","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 15th Asia-Pacific Symposium on Internetware"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3671016.3674819","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3671016.3674819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:38:40Z","timestamp":1755909520000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3671016.3674819"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,24]]},"references-count":43,"alternative-id":["10.1145\/3671016.3674819","10.1145\/3671016"],"URL":"https:\/\/doi.org\/10.1145\/3671016.3674819","relation":{},"subject":[],"published":{"date-parts":[[2024,7,24]]},"assertion":[{"value":"2024-07-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}