{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:00:29Z","timestamp":1750309229479,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of Shanghai","award":["22ZR1407900"],"award-info":[{"award-number":["22ZR1407900"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3663529.3663842","type":"proceedings-article","created":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T19:43:13Z","timestamp":1720640593000},"page":"220-231","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Combating Missed Recalls in E-commerce Search: A CoT-Prompting Testing Approach"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1964-313X","authenticated-orcid":false,"given":"Shengnan","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5099-2335","authenticated-orcid":false,"given":"Yongxiang","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0767-1662","authenticated-orcid":false,"given":"Yingchuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5831-9474","authenticated-orcid":false,"given":"Jiazhen","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7037-977X","authenticated-orcid":false,"given":"Jin","family":"Meng","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7319-6904","authenticated-orcid":false,"given":"Liujie","family":"Fan","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0852-115X","authenticated-orcid":false,"given":"Zhongshi","family":"Luan","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9405-4485","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9184-7383","authenticated-orcid":false,"given":"Yangfan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Toufique Ahmed Supriyo Ghosh Chetan Bansal Thomas Zimmermann Xuchao Zhang and Saravan Rajmohan. 2023. Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models. arXiv preprint arXiv:2301.03797.","DOI":"10.1109\/ICSE48619.2023.00149"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357980"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080813"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-023-03171-8"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-023-03172-7"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Sid Black Gao Leo Phil Wang Connor Leahy and Stella Biderman. 2021. GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow. https:\/\/doi.org\/10.5281\/zenodo.5297715 10.5281\/zenodo.5297715","DOI":"10.5281\/zenodo.5297715"},{"key":"e_1_3_2_1_9_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems, 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, and Amanda Askell. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33 (2020), 1877\u20131901."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/qsic.2005.67"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3143561","article-title":"Metamorphic testing: A review of challenges and opportunities","volume":"51","author":"Chen Tsong Yueh","year":"2018","unstructured":"Tsong Yueh Chen, Fei-Ching Kuo, Huai Liu, Pak-Lok Poon, Dave Towey, TH Tse, and Zhi Quan Zhou. 2018. Metamorphic testing: A review of challenges and opportunities. ACM Computing Surveys (CSUR), 51, 1 (2018), 1\u201327.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0950-5849(02)00129-5"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/met.2019.00010"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458553.3458555"},{"key":"e_1_3_2_1_15_1","volume-title":"Chenyuan Yang, Shizhuo Dylan Zhang, Shujing Yang, and Lingming Zhang.","author":"Deng Yinlin","year":"2023","unstructured":"Yinlin Deng, Chunqiu Steven Xia, Chenyuan Yang, Shizhuo Dylan Zhang, Shujing Yang, and Lingming Zhang. 2023. Large language models are edge-case fuzzers: Testing deep learning libraries via fuzzgpt. arXiv preprint arXiv:2304.02014."},{"key":"e_1_3_2_1_16_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/tase49443.2020.00032"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/icse48619.2023.00128"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767780"},{"key":"e_1_3_2_1_21_1","unstructured":"Shuzheng Gao Xin-Cheng Wen Cuiyun Gao Wenxuan Wang and Michael R Lyu. 2023. Constructing Effective In-Context Demonstration for Code Intelligence Tasks: An Empirical Study. arXiv preprint arXiv:2304.07575."},{"key":"e_1_3_2_1_22_1","volume-title":"Openagi: When llm meets domain experts. arXiv preprint arXiv:2304.04370.","author":"Ge Yingqiang","year":"2023","unstructured":"Yingqiang Ge, Wenyue Hua, Jianchao Ji, Juntao Tan, Shuyuan Xu, and Yongfeng Zhang. 2023. Openagi: When llm meets domain experts. arXiv preprint arXiv:2304.04370."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0950-5849(02)00049-6"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0306-4573(98)00041-7"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409756"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2488388.2488435"},{"key":"e_1_3_2_1_27_1","volume-title":"Measuring search engine quality. Information retrieval, 4, 1","author":"Hawking David","year":"2001","unstructured":"David Hawking, Nick Craswell, Peter Bailey, and Kathleen Griffihs. 2001. Measuring search engine quality. Information retrieval, 4, 1 (2001), 33\u201359."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380339"},{"key":"e_1_3_2_1_29_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_1_31_1","unstructured":"Wenxiang Jiao Wenxuan Wang Jen-tse Huang Xing Wang and Zhaopeng Tu. 2023. Is ChatGPT a good translator? A preliminary study. arXiv preprint arXiv:2301.08745."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/icse48619.2023.00194"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/icse48619.2023.00085"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467101"},{"key":"e_1_3_2_1_35_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190.","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2813885.2737986"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2013.46"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Zhe Liu Chunyang Chen Junjie Wang Mengzhuo Chen Boyu Wu Xing Che Dandan Wang and Qing Wang. 2023. Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions. arXiv preprint arXiv:2310.15780.","DOI":"10.1145\/3597503.3639180"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3547395"},{"volume-title":"Handbook of software reliability engineering. 222","author":"Lyu Michael R","key":"e_1_3_2_1_40_1","unstructured":"Michael R Lyu. 1996. Handbook of software reliability engineering. 222, IEEE computer society press Los Alamitos."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468573"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Sewon Min Xinxi Lyu Ari Holtzman Mikel Artetxe Mike Lewis Hannaneh Hajishirzi and Luke Zettlemoyer. 2022. Rethinking the role of demonstrations: What makes in-context learning work? arXiv preprint arXiv:2202.12837.","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","unstructured":"Christian Murphy Gail E Kaiser and Lifeng Hu. 2008. Properties of machine learning applications for use in metamorphic testing. https:\/\/doi.org\/10.7916\/D8XK8PFD 10.7916\/D8XK8PFD","DOI":"10.7916\/D8XK8PFD"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/prdc.2018.00030"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330759"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1080\/00343404.2021.1910229"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/sp46215.2023.10179324"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.4630260604"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524846.3527338"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2016.2532875"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210152"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.10334"},{"key":"e_1_3_2_1_53_1","volume-title":"Thematic analysis. The SAGE handbook of qualitative research in psychology, 2","author":"Terry Gareth","year":"2017","unstructured":"Gareth Terry, Nikki Hayfield, Victoria Clarke, and Virginia Braun. 2017. Thematic analysis. The SAGE handbook of qualitative research in psychology, 2 (2017), 17\u201337."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180220"},{"key":"e_1_3_2_1_55_1","unstructured":"Christophe Van Gysel. 2017. Remedies against the vocabulary gap in information retrieval. arXiv preprint arXiv:1711.06004."},{"key":"e_1_3_2_1_56_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30 (2017)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0306-4573(03)00043-8"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/icse48619.2023.00200"},{"key":"e_1_3_2_1_59_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35 (2022), 24824\u201324837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/icse48619.2023.00129"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2010.11.920"},{"key":"e_1_3_2_1_62_1","unstructured":"Junjie Ye Xuanting Chen Nuo Xu Can Zu Zekai Shao Shichun Liu Yuhan Cui Zeyang Zhou Chao Gong and Yang Shen. 2023. A comprehensive capability analysis of gpt-3 and gpt-3.5 series models. arXiv preprint arXiv:2303.10420."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534389"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401446"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238187"},{"key":"e_1_3_2_1_66_1","unstructured":"Zhuosheng Zhang Aston Zhang Mu Li and Alex Smola. 2022. Automatic chain of thought prompting in large language models. arXiv preprint arXiv:2210.03493."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2015.2478001"}],"event":{"name":"FSE '24: 32nd ACM International Conference on the Foundations of Software Engineering","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Porto de Galinhas Brazil","acronym":"FSE '24"},"container-title":["Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663529.3663842","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3663529.3663842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:21Z","timestamp":1750290261000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663529.3663842"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":66,"alternative-id":["10.1145\/3663529.3663842","10.1145\/3663529"],"URL":"https:\/\/doi.org\/10.1145\/3663529.3663842","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}