{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T16:17:26Z","timestamp":1779898646048,"version":"3.53.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T00:00:00Z","timestamp":1745625600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T00:00:00Z","timestamp":1745625600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s10664-025-10641-1","type":"journal-article","created":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T11:05:26Z","timestamp":1745665526000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["RAG-Driven multiple assertions generation with large language models"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7768-7312","authenticated-orcid":false,"given":"Zhuang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hailong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongtong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8465-8189","authenticated-orcid":false,"given":"Bei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"10641_CR1","unstructured":"Aghajanyan A, Zettlemoyer L, Gupta S (2020) Intrinsic dimensionality explains the effectiveness of language model fine-tuning. URL https:\/\/arxiv.org\/abs\/2012.13255"},{"key":"10641_CR2","doi-asserted-by":"crossref","unstructured":"Almasi MM, Hemmati H, Fraser G, Arcuri A, Benefelds J (2017) An industrial evaluation of unit test generation: Finding real faults in a financial application. In: 2017 IEEE\/ACM 39th International Conference on Software Engineering: Software Engineering in Practice Track (ICSE-SEIP), pp. 263\u2013272. IEEE","DOI":"10.1109\/ICSE-SEIP.2017.27"},{"issue":"2","key":"10641_CR3","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1109\/TSE.2011.121","volume":"38","author":"A Arcuri","year":"2012","unstructured":"Arcuri A, Iqbal MZ, Briand L (2012) Random testing: Theoretical results and practical implications. IEEE Trans Software Eng 38(2):258\u2013277. https:\/\/doi.org\/10.1109\/TSE.2011.121","journal-title":"IEEE Trans Software Eng"},{"key":"10641_CR4","doi-asserted-by":"publisher","unstructured":"Baresi L, Lanzi PL, Miraz M (2010) Testful: An evolutionary test approach for java. pp. 185\u2013194. https:\/\/doi.org\/10.1109\/ICST.2010.54","DOI":"10.1109\/ICST.2010.54"},{"issue":"1","key":"10641_CR5","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.entcs.2005.12.014","volume":"148","author":"L Baresi","year":"2006","unstructured":"Baresi L, Pezze M (2006) An introduction to software testing. Electron Notes Theor Comput Sci 148(1):89\u2013111","journal-title":"Electron Notes Theor Comput Sci"},{"key":"10641_CR6","doi-asserted-by":"crossref","unstructured":"Beller M, Gousios G, Panichella A, Zaidman A (2015) When, how, and why developers (do not) test in their ides. In: Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering, pp. 179\u2013190","DOI":"10.1145\/2786805.2786843"},{"key":"10641_CR7","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. In: Proceedings of the 34th international conference on Neural Information Processing Systems, NIPS\u201920. Curran Associates Inc., Red Hook, NY, USA"},{"key":"10641_CR8","unstructured":"Deljouyi A, Koohestani R, Izadi M, Zaidman A (2024) Leveraging large language models for enhancing the understandability of generated unit tests. URL https:\/\/arxiv.org\/abs\/2408.11710"},{"key":"10641_CR9","unstructured":"Dettmers T, Pagnoni A, Holtzman A, Zettlemoyer L (2023) Qlora: Efficient finetuning of quantized llms. In: Oh A, Naumann T, Globerson A, Saenko K, Hardt M, Levine S (eds) Advances in neural information processing systems. Curran Associates Inc, pp 10088\u201310115"},{"key":"10641_CR10","doi-asserted-by":"crossref","unstructured":"Fraser G, Arcuri A (2011) Evosuite: automatic test suite generation for object-oriented software. In: Proceedings of the 19th ACM SIGSOFT symposium and the 13th European conference on Foundations of software engineering, pp. 416\u2013419","DOI":"10.1145\/2025113.2025179"},{"key":"10641_CR11","doi-asserted-by":"publisher","unstructured":"Gu J, Lu Z, Li H, Li VO (2016) Incorporating copying mechanism in sequence-to-sequence learning. In: Proceedings of the 54th annual meeting of the association for computational linguistics (Volume 1: Long Papers), pp. 1631\u20131640. Association for Computational Linguistics, Berlin, Germany. https:\/\/doi.org\/10.18653\/v1\/P16-1154. URL https:\/\/aclanthology.org\/P16-1154","DOI":"10.18653\/v1\/P16-1154"},{"issue":"8","key":"10641_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"10641_CR13","doi-asserted-by":"crossref","unstructured":"Hou X, Zhao Y, Liu Y, Yang Z, Wang K, Li L, Luo X, Lo D, Grundy J, Wang H (2024) Large language models for software engineering: A systematic literature review. URL https:\/\/arxiv.org\/abs\/2308.10620","DOI":"10.1145\/3695988"},{"key":"10641_CR14","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2021) Lora: Low-rank adaptation of large language models. URL https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"10641_CR15","unstructured":"Husain H, Wu HH, Gazit T, Allamanis M, Brockschmidt, M (2019) Codesearchnet challenge: Evaluating the state of semantic code search. arXiv:1909.09436"},{"key":"10641_CR16","unstructured":"Jin H, Huang L, Cai H, Yan J, Li B, Chen H (2024) From llms to llm-based agents for software engineering: A survey of current, challenges and future . URL https:\/\/arxiv.org\/abs\/2408.02479"},{"key":"10641_CR17","doi-asserted-by":"crossref","unstructured":"Just R, Jalali D, Ernst MD (2014) Defects4j: A database of existing faults to enable controlled testing studies for java programs. In: Proceedings of the 2014 international symposium on software testing and analysis, pp. 437\u2013440","DOI":"10.1145\/2610384.2628055"},{"issue":"04","key":"10641_CR18","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MS.2004.1","volume":"23","author":"H Kim","year":"2004","unstructured":"Kim H (2004) A process model for successful crm system development. IEEE Softw 23(04):22\u201328. https:\/\/doi.org\/10.1109\/MS.2004.1","journal-title":"IEEE Softw"},{"key":"10641_CR19","doi-asserted-by":"publisher","unstructured":"Koehn P, Knowles R (2017) Six challenges for neural machine translation. In: Proceedings of the first workshop on neural machine translation, pp. 28\u201339. Association for Computational Linguistics, Vancouver. https:\/\/doi.org\/10.18653\/v1\/W17-3204. URL https:\/\/aclanthology.org\/W17-3204","DOI":"10.18653\/v1\/W17-3204"},{"key":"10641_CR20","unstructured":"Kojima T, Gu SS, Reid M, Matsuo Y, Iwasawa Y (2022) Large language models are zero-shot reasoners. In: Koyejo S, Mohamed S, Agarwal A, Belgrave D, Cho K, Oh A (eds) Advances in neural information processing systems, vol 35. Curran Associates Inc, pp 22199\u201322213"},{"key":"10641_CR21","doi-asserted-by":"crossref","unstructured":"Kwon W, Li Z, Zhuang S, Sheng Y, Zheng L, Yu CH, Gonzalez JE, Zhang H, Stoica I (2023) Efficient memory management for large language model serving with pagedattention. In: Proceedings of the ACM SIGOPS 29th symposium on operating systems principles","DOI":"10.1145\/3600006.3613165"},{"key":"10641_CR22","doi-asserted-by":"publisher","unstructured":"Lemieux C, Inala JP, Lahiri SK, Sen S (2023) Codamosa: Escaping coverage plateaus in test generation with pre-trained large language models. In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE), pp. 919\u2013931. https:\/\/doi.org\/10.1109\/ICSE48619.2023.00085","DOI":"10.1109\/ICSE48619.2023.00085"},{"key":"10641_CR23","doi-asserted-by":"publisher","unstructured":"Li TO, Zong W, Wang Y, Tian H, Wang Y, Cheung SC, Kramer J (2023) Nuances are the key: Unlocking chatgpt to find failure-inducing tests with differential prompting. In: 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE), pp. 14\u201326. https:\/\/doi.org\/10.1109\/ASE56229.2023.00089","DOI":"10.1109\/ASE56229.2023.00089"},{"key":"10641_CR24","unstructured":"Liu F, Liu Y, Shi L, Huang H, Wang R, Yang Z, Zhang L, Li Z, Ma Y (2024) Exploring and evaluating hallucinations in llm-powered code generation. URL https:\/\/arxiv.org\/abs\/2404.00971"},{"key":"10641_CR25","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1002\/stvr.294","volume":"14","author":"P McMinn","year":"2004","unstructured":"McMinn P (2004) Search-based software test data generation: a survey: Research articles. Softw Test, Verif Reliab 14:105\u2013156. https:\/\/doi.org\/10.1002\/stvr.294","journal-title":"Softw Test, Verif Reliab"},{"key":"10641_CR26","doi-asserted-by":"publisher","unstructured":"Pacheco C, Ernst M (2005) Eclat: Automatic generation and classification of test inputs. pp. 504\u2013527. https:\/\/doi.org\/10.1007\/11531142_22","DOI":"10.1007\/11531142_22"},{"key":"10641_CR27","doi-asserted-by":"crossref","unstructured":"Pacheco C, Ernst MD (2007) Randoop: feedback-directed random testing for java. In: Companion to the 22nd ACM SIGPLAN conference on Object-oriented programming systems and applications companion, pp. 815\u2013816","DOI":"10.1145\/1297846.1297902"},{"key":"10641_CR28","doi-asserted-by":"publisher","unstructured":"Pacheco C, Lahiri SK, Ernst MD, Ball T (2007) Feedback-directed random test generation. In: 29th International Conference on Software Engineering (ICSE\u201907), pp. 75\u201384.https:\/\/doi.org\/10.1109\/ICSE.2007.37","DOI":"10.1109\/ICSE.2007.37"},{"key":"10641_CR29","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics, pp. 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"10641_CR30","unstructured":"Pizzorno JA, Berger ED (2024) Coverup: Coverage-guided llm-based test generation. URL https:\/\/arxiv.org\/abs\/2403.16218"},{"key":"10641_CR31","unstructured":"Pu G, Jain A, Yin J, Kaplan R (2023) Empirical analysis of the strengths and weaknesses of peft techniques for llms. URL https:\/\/arxiv.org\/abs\/2304.14999"},{"key":"10641_CR32","unstructured":"Qin H, Ma X, Zheng X, Li X, Zhang Y, Liu S, Luo J, Liu X, Magno M (2024) Accurate lora-finetuning quantization of llms via information retention. URL https:\/\/arxiv.org\/abs\/2402.05445"},{"key":"10641_CR33","unstructured":"Radford A, Narasimhan K, Salimans T, Sutskever I (2018) Improving language understanding by generative pre-training. https:\/\/openai.com\/blog\/language-unsupervised\/. URL https:\/\/openai.com\/research\/language-unsupervised"},{"key":"10641_CR34","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I (2019) Language models are unsupervised multitask learners. URL https:\/\/cdn.openai.com\/better-language-models"},{"key":"10641_CR35","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2019) Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv:1910.10683"},{"key":"10641_CR36","unstructured":"Ren S, Guo D, Lu S, Zhou L, Liu S, Tang D, Sundaresan N, Zhou M, Blanco A, Ma S (2020) Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:2009.10297"},{"key":"10641_CR37","doi-asserted-by":"crossref","unstructured":"Roy D, Zhang Z, Ma M, Arnaoudova V, Panichella A, Panichella S, Gonzalez D, Mirakhorli M (2020) Deeptc-enhancer: Improving the readability of automatically generated tests. In: Proceedings of the 35th IEEE\/ACM international conference on automated software engineering, pp. 287\u2013298","DOI":"10.1145\/3324884.3416622"},{"key":"10641_CR38","unstructured":"Rozi\u00e9re B, Gehring J, Gloeckle F, Sootla S, Gat I, Tan XE, Adi Y, Liu J, Sauvestre R, Remez T, Rapin J, Kozhevnikov A, Evtimov I, Bitton J, Bhatt M, Ferrer CC, Grattafiori A, Xiong W, D\u00e9fossez A, Copet J, Azhar F, Touvron H, Martin L, Usunier N, Scialom T, Synnaeve G (2024) Code llama: Open foundation models for code. URL https:\/\/arxiv.org\/abs\/2308.12950"},{"key":"10641_CR39","doi-asserted-by":"publisher","unstructured":"Ryan G, Jain S, Shang M, Wang S, Ma X, Ramanathan MK, Ray B (2024) Code-aware prompting: A study of coverage-guided test generation in regression setting using llm. Proc ACM Softw Eng 1(FSE), 951\u2013971. https:\/\/doi.org\/10.1145\/3643769","DOI":"10.1145\/3643769"},{"issue":"1","key":"10641_CR40","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/TSE.2023.3334955","volume":"50","author":"M Sch\u00e4fer","year":"2024","unstructured":"Sch\u00e4fer M, Nadi S, Eghbali A, Tip F (2024) An empirical evaluation of using large language models for automated unit test generation. IEEE Trans Software Eng 50(1):85\u2013105. https:\/\/doi.org\/10.1109\/TSE.2023.3334955","journal-title":"IEEE Trans Software Eng"},{"key":"10641_CR41","unstructured":"Stefano GD, Sch\u00f6nherr L, Pellegrino G (2024) Rag and roll: An end-to-end evaluation of indirect prompt manipulations in llm-based application frameworks. URL https:\/\/arxiv.org\/abs\/2408.05025"},{"key":"10641_CR42","unstructured":"Tufano M, Drain D, Svyatkovskiy A, Deng SK, Sundaresan N (2020) Unit test case generation with transformers and focal context"},{"key":"10641_CR43","doi-asserted-by":"crossref","unstructured":"Tufano M, Drain D, Svyatkovskiy A, Sundaresan N (2020) Generating accurate assert statements for unit test cases using pretrained transformers. arXiv:2009.05634","DOI":"10.1145\/3460945.3464951"},{"key":"10641_CR44","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. Advances in Neural Information Processing Systems 30"},{"key":"10641_CR45","doi-asserted-by":"publisher","unstructured":"Wang H, Xu T, Wang B (2024a) Deep multiple assertions generation. In: Proceedings of the 2024 IEEE\/ACM first international conference on AI foundation models and software engineering, FORGE \u201924, p. 1-11. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3650105.3652293. URL https:\/\/doi.org\/10.1145\/3650105.3652293","DOI":"10.1145\/3650105.3652293"},{"key":"10641_CR46","doi-asserted-by":"publisher","unstructured":"Wang J, Huang Y, Chen C, Liu Z, Wang S, Wang Q (2024b) Software testing with large language models: Survey, landscape, and vision. IEEE Transactions on Software Engineering PP:1\u201327. https:\/\/doi.org\/10.1109\/TSE.2024.3368208","DOI":"10.1109\/TSE.2024.3368208"},{"key":"10641_CR47","doi-asserted-by":"publisher","unstructured":"Wang S, Shrestha N, Subburaman AK, Wang J, Wei M, Nagappan N (2021) Automatic unit test generation for machine learning libraries: How far are we? In: 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE), pp. 1548\u20131560. https:\/\/doi.org\/10.1109\/ICSE43902.2021.00138","DOI":"10.1109\/ICSE43902.2021.00138"},{"key":"10641_CR48","doi-asserted-by":"crossref","unstructured":"Wang Z, Liu K, Li G, Jin Z (2024c) Hits: High-coverage llm-based unit test generation via method slicing. URL https:\/\/arxiv.org\/abs\/2408.11324","DOI":"10.1145\/3691620.3695501"},{"key":"10641_CR49","doi-asserted-by":"crossref","unstructured":"Watson C, Tufano M, Moran K, Bavota G, Poshyvanyk D (2020) On learning meaningful assert statements for unit test cases. In: Proceedings of the ACM\/IEEE 42nd international conference on software engineering, pp. 1398\u20131409","DOI":"10.1145\/3377811.3380429"},{"key":"10641_CR50","unstructured":"White J, Fu Q, Hays S, Sandborn M, Olea C, Gilbert H, Elnashar A, Spencer-Smith J, Schmidt DC (2023) A prompt pattern catalog to enhance prompt engineering with chatgpt. URL https:\/\/arxiv.org\/abs\/2302.11382"},{"key":"10641_CR51","doi-asserted-by":"crossref","unstructured":"White R, Krinke J (2018) Testnmt: Function-to-test neural machine translation. In: Proceedings of the 4th ACM SIGSOFT international workshop on NLP for software engineering, pp. 30\u201333","DOI":"10.1145\/3283812.3283823"},{"key":"10641_CR52","unstructured":"Xia Y, Wang R, Liu X, Li M, Yu T, Chen X, McAuley J, Li S (2024) Beyond chain-of-thought: A survey of chain-of-x paradigms for llms. URL https:\/\/arxiv.org\/abs\/2404.15676"},{"key":"10641_CR53","doi-asserted-by":"crossref","unstructured":"Yu H, Lou Y, Sun K, Ran D, Xie T, Hao D, Li Y, Li G, Wang Q (2022) Automated assertion generation via information retrieval and its integration with deep learning. ICSE","DOI":"10.1145\/3510003.3510149"},{"key":"10641_CR54","doi-asserted-by":"publisher","unstructured":"Yuan Z, Liu M, Ding S, Wang K, Chen Y, Peng X, Lou Y (2024) Evaluating and improving chatgpt for unit test generation. Proc ACM Softw Eng 1(FSE). https:\/\/doi.org\/10.1145\/3660783. URL https:\/\/doi.org\/10.1145\/3660783","DOI":"10.1145\/3660783"},{"key":"10641_CR55","unstructured":"Zhou D, Sch\u00e4rli N, Hou L, Wei J, Scales N, Wang X, Schuurmans D, Cui C, Bousquet O, Le QV, Chi EH (2023) Least-to-most prompting enables complex reasoning in large language models. In: The eleventh international conference on learning representations"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10641-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-025-10641-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10641-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T09:53:20Z","timestamp":1749117200000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-025-10641-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,26]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10641"],"URL":"https:\/\/doi.org\/10.1007\/s10664-025-10641-1","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,26]]},"assertion":[{"value":"14 March 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}},{"value":"The authors declare that they have no conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"105"}}