{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:47:54Z","timestamp":1784821674914,"version":"3.55.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302021"],"award-info":[{"award-number":["62302021"]}],"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":["62577007"],"award-info":[{"award-number":["62577007"]}],"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":["62332001"],"award-info":[{"award-number":["62332001"]}],"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":["62502283"],"award-info":[{"award-number":["62502283"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Laboratory of Complex & Critical Software Environment","award":["CCSE-2025ZX-09"],"award-info":[{"award-number":["CCSE-2025ZX-09"]}]},{"name":"State Key Laboratory of Complex & Critical Software Environment","award":["CCSE-2024ZX-14"],"award-info":[{"award-number":["CCSE-2024ZX-14"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tse.2026.3657432","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T20:58:33Z","timestamp":1769201913000},"page":"1037-1055","source":"Crossref","is-referenced-by-count":10,"title":["Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3905-8133","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Complex & Critical Software Environment (SKLCCSE), School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8649-7147","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex & Critical Software Environment (SKLCCSE), School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-7213","authenticated-orcid":false,"given":"Lin","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0670-4538","authenticated-orcid":false,"given":"Zhen","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2258-5893","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex & Critical Software Environment (SKLCCSE), School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6100-7068","authenticated-orcid":false,"given":"Xiaoli","family":"Lian","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex & Critical Software Environment (SKLCCSE), School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4864-9592","authenticated-orcid":false,"given":"Zhongqi","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Cloud Computing Technologies Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3304-1389","authenticated-orcid":false,"given":"Yuchi","family":"Ma","sequence":"additional","affiliation":[{"name":"Huawei Cloud Computing Technologies Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"CodeMirage: Hallucinations in code generated by large language models","author":"Agarwal","year":"2024"},{"key":"ref2","article-title":"Amazon codewhisperer.","year":"2023"},{"key":"ref3","article-title":"Program synthesis with large language models","author":"Austin","year":"2021"},{"key":"ref4","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021"},{"key":"ref5","article-title":"DyCodeEval: Dynamic benchmarking of reasoning capabilities in code large language models under data contamination","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3643780"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.431"},{"key":"ref8","article-title":"FacTool: Factuality detection in generative AI\u2013a tool augmented framework for multi-task and multi-domain scenarios","author":"Chern","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ESEM.2011.36"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.212"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.212"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3649825"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-025-4632-8"},{"key":"ref14","first-page":"11733","article-title":"Improving factuality and reasoning in language models through multiagent debate","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Du","year":"2023"},{"key":"ref15","article-title":"Microsoft attracting users to its code-writing, generative ai software.","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1037\/a0037289"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/0031721716647023"},{"key":"ref18","article-title":"InCoder: A generative model for code infilling and synthesis","volume-title":"Proc. ICLR","author":"Fried","year":"2023"},{"key":"ref19","article-title":"DeepSeek-Coder: When the large language model meets programming\u2013the rise of code intelligence","author":"Guo","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref21","first-page":"17685","article-title":"Synthesize, execute and debug: Learning to repair for neural program synthesis","volume":"33","author":"Gupta","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref22","article-title":"Measuring coding challenge competence with apps","author":"Hendrycks","year":"2021"},{"key":"ref23","article-title":"The curious case of neural text degeneration","volume-title":"Proc. ICLR","author":"Holtzman","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3383123"},{"key":"ref26","article-title":"Armando Solar-Lezama, Koushik Sen, and Ion Stoica. Livecodebench: Holistic and contamination free evaluation of large language models for code","author":"Jain","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MSR59073.2023.00082"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref29","article-title":"Collu-Bench: A benchmark for predicting language model hallucinations in code","author":"Jiang","year":"2024"},{"key":"ref30","article-title":"Research: Quantifying GitHub Copilot\u2019s impact on developer productivity and happiness.","author":"Kalliamvakou","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387491"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.367"},{"key":"ref33","first-page":"18319","article-title":"DS-1000: A natural and reliable benchmark for data science code generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lai","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.577"},{"key":"ref35","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.118"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.214"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1797"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1108\/ws.2000.07949fab.004"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq1158"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549081"},{"key":"ref42","article-title":"BatGPT: A bidirectional autoregessive talker from generative pre-trained transformer","author":"Li","year":"2023c"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0943"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695054"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3643674"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2024.3392499"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00026"},{"key":"ref48","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume":"36","author":"Madaan","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"ref50","first-page":"7","article-title":"Reducing hallucinations: Harnessing contextual analysis for AI code generation","author":"Mesbah","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528470"},{"key":"ref52","article-title":"CodeGen2: Lessons for training LLMs on programming and natural languages","author":"Nijkamp","year":"2023a"},{"key":"ref53","article-title":"CodeGen: An open large language model for code with multi-turn program synthesis","volume-title":"Proc. ICLR","author":"Nijkamp","year":"2023b"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.52"},{"key":"ref55","article-title":"ChatGPT: Optimizing language models for dialogue.","year":"2022"},{"key":"ref56","article-title":"Learning to reason with LLMs.","year":"2024"},{"key":"ref57","article-title":"Check your facts and try again: Improving large language models with external knowledge and automated feedback","author":"Peng","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_184700"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1145\/3643795.3648379","article-title":"An empirical study on usage and perceptions of LLMs in a software engineering project","volume-title":"Proc. 1st Int. Workshop Large Lang. Models Code","author":"Rasnayaka","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-021-00801-4"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.344"},{"key":"ref62","first-page":"20601","article-title":"Unsupervised translation of programming languages","volume":"33","author":"Roziere","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref63","article-title":"Code Llama: Open foundation models for code","author":"Roziere","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICSA-C63560.2024.00067"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.46254\/wc01.20240169"},{"key":"ref66","article-title":"We have a package for you! A comprehensive analysis of package hallucinations by code generating LLMs","author":"Spracklen","year":"2024"},{"key":"ref67","article-title":"LLMs\u2019 Reshaping of people, processes, products, and society in software development: A comprehensive exploration with early adopters","author":"Tabarsi","year":"2025"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-025-10614-4"},{"issue":"24","key":"ref69","first-page":"25300","article-title":"CodeHalu: Code hallucinations in LLMs driven by execution-based verification","volume-title":"Proc. CoRR","volume":"39","author":"Tian"},{"key":"ref70","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519665"},{"issue":"5","key":"ref72","first-page":"360","article-title":"Understanding interobserver agreement: The Kappa statistic","volume":"37","author":"Viera","year":"2005","journal-title":"Family Med."},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/icse55347.2025.00014"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.463"},{"key":"ref76","first-page":"59008","article-title":"Fine-grained human feedback gives better rewards for language model training","volume":"36","author":"Wu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00129"},{"key":"ref78","article-title":"Adaptive chameleon or stubborn sloth: Revealing the behavior of large language models in knowledge conflicts","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xie","year":"2023"},{"key":"ref79","article-title":"Evaluating the code quality of AI-assisted code generation tools: An empirical study on GitHub Copilot, Amazon Codewhisperer, and ChatGPT","author":"Yeti\u015ftiren","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623316"},{"key":"ref81","article-title":"No more manual tests? Evaluating and improving ChatGPT for unit test generation","author":"Yuan","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.151"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.45"},{"key":"ref84","first-page":"59670","article-title":"How language model hallucinations can snowball","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2024a"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1162\/coli.a.16"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3728894"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-025-00335-5"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30185"},{"key":"ref89","article-title":"BigCodeBench: Benchmarking code generation with diverse function calls and complex instructions","author":"Zhuo","year":"2024"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/32\/11440029\/11361549.pdf?arnumber=11361549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:38:40Z","timestamp":1773862720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11361549\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":89,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tse.2026.3657432","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"value":"0098-5589","type":"print"},{"value":"1939-3520","type":"electronic"},{"value":"2326-3881","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}