{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T01:40:35Z","timestamp":1772761235658,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T00:00:00Z","timestamp":1713571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,20]]},"DOI":"10.1145\/3643795.3648382","type":"proceedings-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T13:46:19Z","timestamp":1725975979000},"page":"14-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["LLM4TDD: Best Practices for Test Driven Development Using Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7393-8421","authenticated-orcid":false,"given":"Sanyogita","family":"Piya","sequence":"first","affiliation":[{"name":"The University of Texas at Arlington, Arlington, Texas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7400-2218","authenticated-orcid":false,"given":"Allison","family":"Sullivan","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington, Arlington, Texas, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,9,10]]},"reference":[{"key":"e_1_3_2_1_1_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_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1383602.1383644"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Yu Feng Ruben Martins Yuepeng Wang Isil Dillig and Thomas W Reps. 2017. Component-based synthesis for complex APIs. In POPL. 599--612.","DOI":"10.1145\/3009837.3009851"},{"key":"e_1_3_2_1_4_1","volume-title":"The Cost of Poor Software Quality in the US: A 2022 Report.","author":"Consortium for Information and Software Quality.","year":"2023","unstructured":"Consortium for Information and Software Quality. 2023. The Cost of Poor Software Quality in the US: A 2022 Report. (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Incoder: A generative model for code infilling and synthesis. ICLR","author":"Fried Daniel","year":"2022","unstructured":"Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida 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. ICLR (2022)."},{"key":"e_1_3_2_1_6_1","volume-title":"A structured experiment of test-driven development. Information and software Technology 46, 5","author":"George Boby","year":"2004","unstructured":"Boby George and Laurie Williams. 2004. A structured experiment of test-driven development. Information and software Technology 46, 5 (2004), 337--342."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Sumit Gulwani Oleksandr Polozov Rishabh Singh et al. 2017. Program synthesis. Foundations and Trends\u00ae in Programming Languages 4 1--2 (2017) 1--119.","DOI":"10.1561\/2500000010"},{"key":"e_1_3_2_1_8_1","volume-title":"Mapping language to code in programmatic context. arXiv preprint arXiv:1808.09588","author":"Iyer Srinivasan","year":"2018","unstructured":"Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, and Luke Zettlemoyer. 2018. Mapping language to code in programmatic context. arXiv preprint arXiv:1808.09588 (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2008.34"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00194"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Naoki Kobayashi Taro Sekiyama Issei Sato and Hiroshi Unno. 2021. Toward neural-network-guided program synthesis and verification. In SAS. 236--260.","DOI":"10.1007\/978-3-030-88806-0_12"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v30i4.2262"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Tak Yeon Lee Casey Dugan and Benjamin B Bederson. 2017. Towards understanding human mistakes of programming by example: an online user study. In IUI. 257--261.","DOI":"10.1145\/3025171.3025203"},{"key":"e_1_3_2_1_14_1","unstructured":"LeetCode. 2023. https:\/\/leetcode.com\/. (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00085"},{"key":"e_1_3_2_1_16_1","volume-title":"Fill in the blank: Context-aware automated text input generation for mobile gui testing","author":"Liu Zhe","unstructured":"Zhe Liu, Chunyang Chen, Junjie Wang, Xing Che, Yuekai Huang, Jun Hu, and Qing Wang. 2023. Fill in the blank: Context-aware automated text input generation for mobile gui testing. In ICSE. IEEE, 1355--1367."},{"key":"e_1_3_2_1_17_1","volume-title":"No Need to Lift a Finger Anymore? Assessing the Quality of Code Generation by ChatGPT. arXiv preprint arXiv:2308.04838","author":"Liu Zhijie","year":"2023","unstructured":"Zhijie Liu, Yutian Tang, Xiapu Luo, Yuming Zhou, and Liang Feng Zhang. 2023. No Need to Lift a Finger Anymore? Assessing the Quality of Code Generation by ChatGPT. arXiv preprint arXiv:2308.04838 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/362566.362568"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"E Michael Maximilien and Laurie Williams. 2003. Assessing test-driven development at IBM. In ICSE. 564--569.","DOI":"10.1109\/ICSE.2003.1201238"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Nhan Nguyen and Sarah Nadi. 2022. An empirical evaluation of GitHub copilot's code suggestions. In MSR. 1--5.","DOI":"10.1145\/3524842.3528470"},{"key":"e_1_3_2_1_21_1","volume-title":"Raymond J Mooney, and Milos Gligoric.","author":"Nie Pengyu","year":"2023","unstructured":"Pengyu Nie, Rahul Banerjee, Junyi Jessy Li, Raymond J Mooney, and Milos Gligoric. 2023. Learning Deep Semantics for Test Completion. arXiv preprint arXiv:2302.10166 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Codegen: An open large language model for code with multi-turn program synthesis. arXiv preprint arXiv:2203.13474","author":"Nijkamp Erik","year":"2022","unstructured":"Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. 2022. Codegen: An open large language model for code with multi-turn program synthesis. arXiv preprint arXiv:2203.13474 (2022)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-012-9229-5"},{"key":"e_1_3_2_1_24_1","volume-title":"An empirical evaluation of using large language models for automated unit test generation","author":"Sch\u00e4fer Max","year":"2023","unstructured":"Max Sch\u00e4fer, Sarah Nadi, Aryaz Eghbali, and Frank Tip. 2023. An empirical evaluation of using large language models for automated unit test generation. IEEE Transactions on Software Engineering (2023)."},{"key":"e_1_3_2_1_25_1","first-page":"260","article-title":"Inferring LISP Programs From Examples","volume":"75","author":"Shaw David E","year":"1975","unstructured":"David E Shaw, William R Swartout, and C Cordell Green. 1975. Inferring LISP Programs From Examples.. In IJCAI, Vol. 75. 260--267.","journal-title":"IJCAI"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Armando Solar-Lezama Liviu Tancau Rastislav Bodik Sanjit Seshia and Vijay Saraswat. 2006. Combinatorial sketching for finite programs. In ASPLOS. 404--415.","DOI":"10.1145\/1168918.1168907"},{"key":"e_1_3_2_1_27_1","volume-title":"PROW: A step toward automatic program writing. In IJCAI. 241--252.","author":"Waldinger Richard J","year":"1969","unstructured":"Richard J Waldinger and Richard CT Lee. 1969. PROW: A step toward automatic program writing. In IJCAI. 241--252."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Frank F Xu Uri Alon Graham Neubig and Vincent Josua Hellendoorn. 2022. A systematic evaluation of large language models of code. In MAPS. 1--10.","DOI":"10.1145\/3520312.3534862"}],"event":{"name":"LLM4Code '24: 1st International Workshop on Large Language Models for Code","location":"Lisbon Portugal","acronym":"LLM4Code '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the 1st International Workshop on Large Language Models for Code"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643795.3648382","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3643795.3648382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:45Z","timestamp":1750294665000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643795.3648382"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,20]]},"references-count":28,"alternative-id":["10.1145\/3643795.3648382","10.1145\/3643795"],"URL":"https:\/\/doi.org\/10.1145\/3643795.3648382","relation":{},"subject":[],"published":{"date-parts":[[2024,4,20]]},"assertion":[{"value":"2024-09-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}