{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T07:17:01Z","timestamp":1783408621633,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3786181.3788730","type":"proceedings-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:28:24Z","timestamp":1783405704000},"page":"14-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An Automated Methodology for Generating Labeled Datasets of Semantic Errors in Code"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9449-213X","authenticated-orcid":false,"given":"Mahmoud","family":"Kassem","sequence":"first","affiliation":[{"name":"New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0427-4503","authenticated-orcid":false,"given":"Francisco","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0091-6030","authenticated-orcid":false,"given":"Sarah","family":"Nadi","sequence":"additional","affiliation":[{"name":"New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","unstructured":"Altaf\u00a0Allah Abbassi Leuson Da\u00a0Silva Amin Nikanjam and Foutse Khomh. 2025. Unveiling Inefficiencies in LLM-Generated Code: Toward a Comprehensive Taxonomy. arxiv:https:\/\/arXiv.org\/abs\/2503.06327\u00a0[cs.SE] 10.48550\/arXiv.2503.06327","DOI":"10.48550\/arXiv.2503.06327"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44503-X_27"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"E. Akimova I. Klyuchnikov N. Sorokin et\u00a0al. 2021. A Survey on Software Defect Prediction Using Deep Learning. Mathematics 9 24 (2021) 3281.","DOI":"10.3390\/math9111180"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/APSEC53868.2021.00022"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Miltiadis Allamanis Earl\u00a0T. Barr Premkumar Devanbu and Charles Sutton. 2018. A Survey of Machine Learning for Big Code and Naturalness. ACM Comput. Surv. 51 4 Article 81 (July 2018) 37\u00a0pages. 10.1145\/3212695","DOI":"10.1145\/3212695"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/STI59943.2023.10255392"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le and Charles Sutton. 2021. Program Synthesis with Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2108.07732\u00a0[cs.PL] 10.48550\/arXiv.2108.07732","DOI":"10.48550\/arXiv.2108.07732"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Yoshua Bengio Aaron Courville and Pascal Vincent. 2013. Representation Learning: A Review and New Perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence 35 8 (2013) 1798\u20131828. 10.1109\/TPAMI.2013.50","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Satish Chandra and Maxim Tabachnyk. 2024. AI in Software Engineering at Google: Progress and the Path Ahead. Google Research Blog. https:\/\/research.google\/blog\/ai-in-software-engineering-at-google-progress-and-the-path-ahead\/","DOI":"10.1145\/3664646.3676277"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Mark Chen Jerry Tworek Heewoo Jun et\u00a0al. 2021. Evaluating Large Language Models Trained on Code. arxiv:https:\/\/arXiv.org\/abs\/2107.03374\u00a0[cs.LG] 10.48550\/arXiv.2107.03374","DOI":"10.48550\/arXiv.2107.03374"},{"key":"e_1_3_3_2_12_2","unstructured":"QiHong Chen Jiachen Yu Jiawei Li Jiecheng Deng Justin Tian\u00a0Jin Chen and Iftekhar Ahmed. 2024. A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why? arxiv:https:\/\/arXiv.org\/abs\/2411.01414\u00a0[cs.SE]"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Xinyun Chen Maxwell Lin Nathanael Sch\u00e4rli and Denny Zhou. 2023. Teaching Large Language Models to Self-Debug. arxiv:https:\/\/arXiv.org\/abs\/2304.05128\u00a0[cs.CL] 10.48550\/arXiv.2304.05128","DOI":"10.48550\/arXiv.2304.05128"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1794"},{"key":"e_1_3_3_2_15_2","unstructured":"Shihan Dou Haoxiang Jia Shenxi Wu Huiyuan Zheng Weikang Zhou Muling Wu Mingxu Chai Jessica Fan Caishuang Huang Yunbo Tao Yan Liu Enyu Zhou Ming Zhang Yuhao Zhou Yueming Wu Rui Zheng Ming Wen Rongxiang Weng Jingang Wang Xunliang Cai Tao Gui Xipeng Qiu Qi Zhang and Xuanjing Huang. 2024. What\u2019s Wrong with Your Code Generated by Large Language Models? An Extensive Study. arxiv:https:\/\/arXiv.org\/abs\/2407.06153\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2407.06153"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_3_2_17_2","unstructured":"Jiawei Gu Xuhui Jiang Zhichao Shi Hexiang Tan Xuehao Zhai Chengjin Xu Wei Li Yinghan Shen Shengjie Ma Honghao Liu Saizhuo Wang Kun Zhang Yuanzhuo Wang Wen Gao Lionel Ni and Jian Guo. 2025. A Survey on LLM-as-a-Judge. arxiv:https:\/\/arXiv.org\/abs\/2411.15594\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2411.15594"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"e_1_3_3_2_19_2","volume-title":"International Conference on Learning Representations","author":"Guo D.","year":"2021","unstructured":"D. Guo, S. Ren, S. Lu, et\u00a0al. 2021. GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_20_2","unstructured":"Jingxuan He Luca Beurer-Kellner and Martin Vechev. 2022. On Distribution Shift in Learning-based Bug Detectors. arxiv:https:\/\/arXiv.org\/abs\/2204.10049\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2204.10049"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00163"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387504"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2013.6624018"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/1028664.1028717"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Kai Huang Zhengzi Xu Su Yang Hongyu Sun Xuejun Li Zheng Yan and Yuqing Zhang. 2023. A Survey on Automated Program Repair Techniques. arxiv:https:\/\/arXiv.org\/abs\/2303.18184\u00a0[cs.SE] 10.48550\/arXiv.2303.18184","DOI":"10.48550\/arXiv.2303.18184"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696630.3728566"},{"key":"e_1_3_3_2_27_2","unstructured":"Albert\u00a0Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Emma\u00a0Bou Hanna Florian Bressand Gianna Lengyel Guillaume Bour Guillaume Lample L\u00e9lio\u00a0Renard Lavaud Lucile Saulnier Marie-Anne Lachaux Pierre Stock Sandeep Subramanian Sophia Yang Szymon Antoniak Teven\u00a0Le Scao Th\u00e9ophile Gervet Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William\u00a0El Sayed. 2024. Mixtral of Experts. arxiv:https:\/\/arXiv.org\/abs\/2401.04088\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.04088"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00069"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628055"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628055"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME58846.2023.00017"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387491"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3653444"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Claire Le\u00a0Goues Neal Holtschulte Edward\u00a0K. Smith Yuriy Brun Premkumar Devanbu Stephanie Forrest and Westley Weimer. 2015. The ManyBugs and IntroClass Benchmarks for Automated Repair of C Programs. IEEE Transactions on Software Engineering 41 12 (2015) 1236\u20131256. 10.1109\/TSE.2015.2454513","DOI":"10.1109\/TSE.2015.2454513"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Meir\u00a0M. Lehman. 1979. On understanding laws evolution and conservation in the large-program life cycle. Journal of Systems and Software 1 3 (jul 1979) 213\u2013221. 10.1016\/0164-1212(79)90022-0","DOI":"10.1016\/0164-1212(79)90022-0"},{"key":"e_1_3_3_2_36_2","unstructured":"Xiaoli Lian Shuaisong Wang Jieping Ma Fang Liu Xin Tan Li Zhang Lin Shi and Cuiyun Gao. 2024. Uncovering Weaknesses in Neural Code Generation. arxiv:https:\/\/arXiv.org\/abs\/2407.09793\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2407.09793"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0943"},{"key":"e_1_3_3_2_38_2","unstructured":"Shukai Liu Linzheng Chai Jian Yang Jiajun Shi He Zhu Liran Wang Ke Jin Wei Zhang Hualei Zhu Shuyue Guo Tao Sun Jiaheng Liu Yunlong Duan Yu Hao Liqun Yang Guanglin Niu Ge Zhang and Zhoujun Li. 2025. MdEval: Massively Multilingual Code Debugging. arxiv:https:\/\/arXiv.org\/abs\/2411.02310\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2411.02310"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/1346281.1346323"},{"key":"e_1_3_3_2_40_2","unstructured":"Wei Ma Shangqing Liu Zhihao Lin Wenhan Wang Qiang Hu Ye Liu Cen Zhang Liming Nie Li Li and Yang Liu. 2023. The LMs: Understanding Code Syntax and Semantics for Code Analysis. arxiv:https:\/\/arXiv.org\/abs\/2305.12138\u00a0[cs.LG]"},{"key":"e_1_3_3_2_41_2","volume-title":"The Living Review on Automated Program Repair","author":"Monperrus Martin","year":"2018","unstructured":"Martin Monperrus. 2018. The Living Review on Automated Program Repair. Technical Report hal-01956501. HAL\/archives-ouvertes.fr."},{"key":"e_1_3_3_2_42_2","unstructured":"Doha Nam Taehyoun Kim Duksan Ryu and Jongmoon Baik. 2025. Probing Pre-trained Language Models on Code Changes: Insights from ReDef a High-Confidence Just-in-Time Defect Prediction Dataset. arxiv:https:\/\/arXiv.org\/abs\/2509.09192\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2509.09192"},{"key":"e_1_3_3_2_43_2","unstructured":"Md\u00a0Nahidul\u00a0Islam Opu Shaowei Wang and Shaiful Chowdhury. 2025. LLM-Based Detection of Tangled Code Changes for Higher-Quality Method-Level Bug Datasets. arxiv:https:\/\/arXiv.org\/abs\/2505.08263\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2505.08263"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409693"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","unstructured":"Shaoming Qiu Bicong E Jingjie He and Liangyu Liu. 2024. Survey of Software Defect Prediction Features. Neural Computing and Applications 37 4 (dec 2024) 2113\u20132144. 10.1007\/s00521-024-10937-1","DOI":"10.1007\/s00521-024-10937-1"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.255"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Henry\u00a0Gordon Rice. 1953. Classes of Recursively Enumerable Sets and Their Decision Problems. Trans. Amer. Math. Soc. 74 2 (1953) 358\u2013366. 10.2307\/1990888","DOI":"10.2307\/1990888"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528505"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Agnia Sergeyuk Yaroslav Golubev Timofey Bryksin and Iftekhar Ahmed. 2024. Using AI-Based Coding Assistants in Practice: State of Affairs Perceptions and Ways Forward. arxiv:https:\/\/arXiv.org\/abs\/2406.07765\u00a0[cs.SE]","DOI":"10.2139\/ssrn.4900362"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00201"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Florian Tambon Arghavan\u00a0Moradi Dakhel Amin Nikanjam Foutse Khomh Michel\u00a0C. Desmarais and Giuliano Antoniol. 2024. Bugs in Large Language Models Generated Code: An Empirical Study. arxiv:https:\/\/arXiv.org\/abs\/2403.08937\u00a0[cs.SE] 10.48550\/arXiv.2403.08937","DOI":"10.48550\/arXiv.2403.08937"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","unstructured":"Florian Tambon Arghavan Moradi-Dakhel Amin Nikanjam Foutse Khomh Michel\u00a0C. Desmarais and Giuliano Antoniol. 2025. Bugs in large language models generated code: an empirical study. Empirical Softw. Engg. 30 3 (Feb. 2025) 48\u00a0pages. 10.1007\/s10664-025-10614-4","DOI":"10.1007\/s10664-025-10614-4"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.247"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","unstructured":"Frank Tip Jonathan Bell and Max Sch\u00e4fer. 2025. LLMorpheus: Mutation Testing Using Large Language Models. IEEE Transactions on Software Engineering 51 6 (2025) 1645\u20131665. 10.1109\/TSE.2025.3562025","DOI":"10.1109\/TSE.2025.3562025"},{"key":"e_1_3_3_2_55_2","unstructured":"Weixi Tong and Tianyi Zhang. 2024. CodeJudge: Evaluating Code Generation with Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2410.02184\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2410.02184"},{"key":"e_1_3_3_2_56_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arxiv:https:\/\/arXiv.org\/abs\/2302.13971\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2019.00046"},{"key":"e_1_3_3_2_58_2","unstructured":"Z. Wang H. Zhang L. Zhang et\u00a0al. 2024. RFCScan: An Autonomous Agent for Detecting Functional Bugs in Network Protocol Implementations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.08447 (2024)."},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00180"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER60148.2024.00084"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417943"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","unstructured":"W.\u00a0Eric Wong Ruizhi Gao Yihao Li Rui Abreu and Franz Wotawa. 2016. A Survey on Software Fault Localization. IEEE Transactions on Software Engineering 42 8 (2016) 707\u2013740. 10.1109\/TSE.2016.2521368","DOI":"10.1109\/TSE.2016.2521368"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","unstructured":"Angus Yang Zehan Li and Jie Li. 2024. Advancing GenAI Assisted Programming\u2013A Comparative Study on Prompt Efficiency and Code Quality Between GPT-4 and GLM-4. arxiv:https:\/\/arXiv.org\/abs\/2402.12782\u00a0[cs.SE] 10.48550\/arXiv.2402.12782","DOI":"10.48550\/arXiv.2402.12782"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER50967.2021.00018"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","unstructured":"Hao Zhong Tao Xie Lu Zhang Jian Pei and Hong Mei. 2009. MAPO: Mining and Recommending API Usage Patterns. 318\u2013343. 10.1007\/978-3-642-03013-0_15","DOI":"10.1007\/978-3-642-03013-0_15"},{"key":"e_1_3_3_2_66_2","unstructured":"Hao-Nan Zhu Robert\u00a0M. Furth Michael Pradel and Cindy Rubio-Gonz\u00e1lez. 2025. From Bugs to Benchmarks: A Comprehensive Survey of Software Defect Datasets. CoRR abs\/2504.17977 (2025). https:\/\/arxiv.org\/abs\/2504.17977"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00195"},{"key":"e_1_3_3_2_68_2","unstructured":"Terry\u00a0Yue Zhuo. 2024. ICE-Score: Instructing Large Language Models to Evaluate Code. arxiv:https:\/\/arXiv.org\/abs\/2304.14317\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2304.14317"},{"key":"e_1_3_3_2_69_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhuo Terry\u00a0Yue","year":"2025","unstructured":"Terry\u00a0Yue Zhuo, Minh\u00a0Chien Vu, Jenny Chim, Han Hu, et\u00a0al. 2025. BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions. In International Conference on Learning Representations (ICLR)."}],"event":{"name":"LLM4Code '26: 3rd International Workshop on Large Language Models For Code","location":"Rio de Janeiro Brazil","acronym":"LLM4Code '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the 3rd International Workshop on Large Language Models For Code"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786181.3788730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:31:26Z","timestamp":1783405886000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786181.3788730"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":68,"alternative-id":["10.1145\/3786181.3788730","10.1145\/3786181"],"URL":"https:\/\/doi.org\/10.1145\/3786181.3788730","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}