{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T02:48:58Z","timestamp":1784342938690,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192731"],"award-info":[{"award-number":["62192731"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192730"],"award-info":[{"award-number":["62192730"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61690200"],"award-info":[{"award-number":["61690200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3691620.3695054","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T15:39:19Z","timestamp":1729265959000},"page":"570-581","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["GraphCoder: Enhancing Repository-Level Code Completion via Coarse-to-fine Retrieval Based on Code Context Graph"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4603-4227","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"first","affiliation":[{"name":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing, China"},{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4707-4418","authenticated-orcid":false,"given":"Ailun","family":"Yu","sequence":"additional","affiliation":[{"name":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing, China"},{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4269-8543","authenticated-orcid":false,"given":"Daoguang","family":"Zan","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0825-8001","authenticated-orcid":false,"given":"Bo","family":"Shen","sequence":"additional","affiliation":[{"name":"Huawei Cloud Computing Technologies Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1543-0196","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing, China"},{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3600-8923","authenticated-orcid":false,"given":"Haiyan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing, China"},{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1087-226X","authenticated-orcid":false,"given":"Zhi","family":"Jin","sequence":"additional","affiliation":[{"name":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing, China"},{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1322-2476","authenticated-orcid":false,"given":"Qianxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/390013.808479"},{"key":"e_1_3_2_1_3_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_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/115372.115320"},{"key":"e_1_3_2_1_5_1","volume-title":"Hantian Ding, Ming Tan, Nihal Jain, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang.","author":"Ding Yangruibo","year":"2023","unstructured":"Yangruibo Ding, Zijian Wang, Wasi Uddin Ahmad, Hantian Ding, Ming Tan, Nihal Jain, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang. 2023. CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion. In Advances in Neural Information Processing Systems 36."},{"key":"e_1_3_2_1_6_1","volume-title":"Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang.","author":"Ding Yangruibo","year":"2022","unstructured":"Yangruibo Ding, Zijian Wang, Wasi Uddin Ahmad, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang. 2022. Cocomic: Code completion by jointly modeling in-file and cross-file context. arXiv preprint arXiv:2212.10007 (2022)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/24039.24041"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.2478\/v10006-010-0056-9"},{"key":"e_1_3_2_1_10_1","volume-title":"GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations.","author":"Guo Daya","year":"2020","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, LIU Shujie, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, et al. 2020. GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_11_1","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Y. Wu Y. K. Li Fuli Luo Yingfei Xiong and Wenfeng Liang. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence. arXiv:2401.14196 [cs.SE]"},{"key":"e_1_3_2_1_12_1","volume-title":"FT2Ra: A Fine-Tuning-Inspired Approach to Retrieval-Augmented Code Completion. arXiv preprint arXiv:2404.01554","author":"Guo Qi","year":"2024","unstructured":"Qi Guo, Xiaohong Li, Xiaofei Xie, Shangqing Liu, Ze Tang, Ruitao Feng, Junjie Wang, Jidong Ge, and Lei Bu. 2024. FT2Ra: A Fine-Tuning-Inspired Approach to Retrieval-Augmented Code Completion. arXiv preprint arXiv:2404.01554 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/174146.154268"},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Data Engineering. IEEE, 38--38","author":"He Huahai","year":"2006","unstructured":"Huahai He and Ambuj K Singh. 2006. Closure-tree: An index structure for graph queries. In International Conference on Data Engineering. IEEE, 38--38."},{"key":"e_1_3_2_1_15_1","volume-title":"The distribution of the flora in the alpine zone. 1. New phytologist 11, 2","author":"Jaccard Paul","year":"1912","unstructured":"Paul Jaccard. 1912. The distribution of the flora in the alpine zone. 1. New phytologist 11, 2 (1912), 37--50."},{"key":"e_1_3_2_1_16_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_17_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_18_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. 2023. StarCoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Context-aware code generation framework for code repositories: Local, global, and third-party library awareness. arXiv preprint arXiv:2312.05772","author":"Liao Dianshu","year":"2023","unstructured":"Dianshu Liao, Shidong Pan, Qing Huang, Xiaoxue Ren, Zhenchang Xing, Huan Jin, and Qinying Li. 2023. Context-aware code generation framework for code repositories: Local, global, and third-party library awareness. arXiv preprint arXiv:2312.05772 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems. arXiv preprint arXiv:2306.03091","author":"Liu Tianyang","year":"2023","unstructured":"Tianyang Liu, Canwen Xu, and Julian McAuley. 2023. RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems. arXiv preprint arXiv:2306.03091 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20522"},{"key":"e_1_3_2_1_23_1","volume-title":"Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, et al.","author":"Lozhkov Anton","year":"2024","unstructured":"Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, et al. 2024. StarCoder 2 and The Stack v2: The Next Generation. arXiv preprint arXiv:2402.19173 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.431"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/322609.322862"},{"key":"e_1_3_2_1_26_1","volume-title":"Codegen2: Lessons for training llms on programming and natural languages. arXiv preprint arXiv:2305.02309","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. arXiv preprint arXiv:2305.02309 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.232"},{"key":"e_1_3_2_1_28_1","volume-title":"RepoHyper: Better Context Retrieval Is All You Need for Repository-Level Code Completion. arXiv preprint arXiv:2403.06095","author":"Phan Huy N","year":"2024","unstructured":"Huy N Phan, Hoang N Phan, Tien N Nguyen, and Nghi DQ Bui. 2024. RepoHyper: Better Context Retrieval Is All You Need for Repository-Level Code Completion. arXiv preprint arXiv:2403.06095 (2024)."},{"key":"e_1_3_2_1_29_1","first-page":"22518","article-title":"Greed: A neural framework for learning graph distance functions","volume":"35","author":"Ranjan Rishabh","year":"2022","unstructured":"Rishabh Ranjan, Siddharth Grover, Sourav Medya, Venkatesan Chakaravarthy, Yogish Sabharwal, and Sayan Ranu. 2022. Greed: A neural framework for learning graph distance functions. Advances in Neural Information Processing Systems 35 (2022), 22518--22530.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","volume-title":"Approximate graph edit distance in quadratic time","author":"Riesen Kaspar","year":"2015","unstructured":"Kaspar Riesen, Miquel Ferrer, and Horst Bunke. 2015. Approximate graph edit distance in quadratic time. IEEE\/ACM transactions on computational biology and bioinformatics 17, 2 (2015), 483--494."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-18224-7_1"},{"key":"e_1_3_2_1_32_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--389.","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_33_1","volume-title":"Yossi Adi, Jingyu Liu, Tal Remez, J\u00e9r\u00e9my Rapin, 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, 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_34_1","volume-title":"International Conference on Machine Learning. PMLR, 31210--31227","author":"Shi Freda","year":"2023","unstructured":"Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed H Chi, Nathanael Sch\u00e4rli, and Denny Zhou. 2023. Large language models can be easily distracted by irrelevant context. In International Conference on Machine Learning. PMLR, 31210--31227."},{"key":"e_1_3_2_1_35_1","volume-title":"RepoFusion: Training Code Models to Understand Your Repository. arXiv preprint arXiv:2306.10998","author":"Shrivastava Disha","year":"2023","unstructured":"Disha Shrivastava, Denis Kocetkov, Harm de Vries, Dzmitry Bahdanau, and Torsten Scholak. 2023. RepoFusion: Training Code Models to Understand Your Repository. arXiv preprint arXiv:2306.10998 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"International Conference on Machine Learning. PMLR, 31693--31715","author":"Shrivastava Disha","year":"2023","unstructured":"Disha Shrivastava, Hugo Larochelle, and Daniel Tarlow. 2023. Repository-level prompt generation for large language models of code. In International Conference on Machine Learning. PMLR, 31693--31715."},{"key":"e_1_3_2_1_37_1","volume-title":"Prompt-based Code Completion via Multi-Retrieval Augmented Generation. arXiv preprint arXiv:2405.07530","author":"Tan Hanzhuo","year":"2024","unstructured":"Hanzhuo Tan, Qi Luo, Ling Jiang, Zizheng Zhan, Jing Li, Haotian Zhang, and Yuqun Zhang. 2024. Prompt-based Code Completion via Multi-Retrieval Augmented Generation. arXiv preprint arXiv:2405.07530 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00076"},{"key":"e_1_3_2_1_39_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_40_1","volume-title":"Making retrieval-augmented language models robust to irrelevant context. arXiv preprint arXiv:2310.01558","author":"Yoran Ori","year":"2023","unstructured":"Ori Yoran, Tomer Wolfson, Ori Ram, and Jonathan Berant. 2023. Making retrieval-augmented language models robust to irrelevant context. arXiv preprint arXiv:2310.01558 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/329"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.411"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687631"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.151"},{"key":"e_1_3_2_1_45_1","unstructured":"Ziyin Zhang Chaoyu Chen Bingchang Liu Cong Liao Zi Gong Hang Yu Jianguo Li and Rui Wang. 2023. Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code. arXiv:2311.07989 [cs.CL]"},{"key":"e_1_3_2_1_46_1","unstructured":"Zibin Zheng Kaiwen Ning Yanlin Wang Jingwen Zhang Dewu Zheng Mingxi Ye and Jiachi Chen. 2023. A Survey of Large Language Models for Code: Evolution Benchmarking and Future Trends. arXiv:2311.10372 [cs.SE]"}],"event":{"name":"ASE '24: 39th IEEE\/ACM International Conference on Automated Software Engineering","location":"Sacramento CA USA","acronym":"ASE '24","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS"]},"container-title":["Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3691620.3695054","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3691620.3695054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:07Z","timestamp":1750291447000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3691620.3695054"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":46,"alternative-id":["10.1145\/3691620.3695054","10.1145\/3691620"],"URL":"https:\/\/doi.org\/10.1145\/3691620.3695054","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2024-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}