{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T08:54:59Z","timestamp":1766566499971,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,17]]},"DOI":"10.1145\/3756681.3756985","type":"proceedings-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T08:30:04Z","timestamp":1766565004000},"page":"1035-1044","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Models as Robust Data Generators in Software Analytics: Are We There Yet?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5760-8211","authenticated-orcid":false,"given":"Md. Abdul","family":"Awal","sequence":"first","affiliation":[{"name":"Software Research Lab, University of Saskatchewan, Saskatoon, Saskatchewan, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9513-6573","authenticated-orcid":false,"given":"Mrigank","family":"Rochan","sequence":"additional","affiliation":[{"name":"University of Saskatchewan, Saskatoon, Saskatchewan, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0519-6164","authenticated-orcid":false,"given":"Chanchal K.","family":"Roy","sequence":"additional","affiliation":[{"name":"Software Research Lab, University of Saskatchewan, Saskatoon, Saskatchewan, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Wasi\u00a0Uddin Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2021. Unified pre-training for program understanding and generation. arXiv:https:\/\/arXiv.org\/abs\/2103.06333 (2021).","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"e_1_3_3_2_3_2","unstructured":"Toufique Ahmed Premkumar Devanbu Christoph Treude and Michael Pradel. 2024. Can LLMs Replace Manual Annotation of Software Engineering Artifacts? arXiv:https:\/\/arXiv.org\/abs\/2408.05534 (2024)."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639183"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWSC50091.2020.9047643"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME58846.2023.00013"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWSC55060.2022.00015"},{"key":"e_1_3_3_2_8_2","unstructured":"Arian Askari Mohammad Aliannejadi Evangelos Kanoulas and Suzan Verberne. 2023. Generating synthetic documents for cross-encoder re-rankers: A comparative study of chatgpt and human experts. arXiv:https:\/\/arXiv.org\/abs\/2305.02320 (2023)."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Md.\u00a0Abdul Awal Mrigank Rochan and Chanchal\u00a0K. Roy. 2025. Replication Package for \"Large Language Models as Robust Data Generators in Software Analytics: Are We There Yet?\". 10.5281\/zenodo.14783616","DOI":"10.5281\/zenodo.14783616"},{"key":"e_1_3_3_2_10_2","unstructured":"Anna Bavaresco Raffaella Bernardi Leonardo Bertolazzi Desmond Elliott Raquel Fern\u00e1ndez Albert Gatt Esam Ghaleb Mario Giulianelli Michael Hanna Alexander Koller et\u00a0al. 2024. Llms instead of human judges? a large scale empirical study across 20 nlp evaluation tasks. arXiv:https:\/\/arXiv.org\/abs\/2406.18403 (2024)."},{"key":"e_1_3_3_2_11_2","unstructured":"Domenico Cotroneo Cristina Improta Pietro Liguori and Roberto Natella. 2023. Vulnerabilities in ai code generators: Exploring targeted data poisoning attacks. arXiv:https:\/\/arXiv.org\/abs\/2308.04451 (2023)."},{"key":"e_1_3_3_2_12_2","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616356"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510150"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Z. Feng D. Guo D. Tang N. Duan X. Feng M. Gong L. Shou Bing Qin T. Liu D. Jiang et\u00a0al. 2020. Codebert: A pre-trained model for programming and natural languages. arXiv:https:\/\/arXiv.org\/abs\/2002.08155 (2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Siddhant Garg and Goutham Ramakrishnan. 2020. Bae: Bert-based adversarial examples for text classification. arXiv:https:\/\/arXiv.org\/abs\/2004.01970 (2020).","DOI":"10.18653\/v1\/2020.emnlp-main.498"},{"key":"e_1_3_3_2_17_2","unstructured":"Biyang Guo Xin Zhang Ziyuan Wang Minqi Jiang Jinran Nie Yuxuan Ding Jianwei Yue and Yupeng Wu. 2023. How close is chatgpt to human experts? comparison corpus evaluation and detection. arXiv:https:\/\/arXiv.org\/abs\/2301.07597 (2023)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Yuepu Guo Rodrigo\u00a0Oliveira Sp\u00ednola and Carolyn Seaman. 2016. Exploring the costs of technical debt management\u2013a case study. Empirical Software Engineering 21 (2016) 159\u2013182.","DOI":"10.1007\/s10664-014-9351-7"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Sivana Hamer Marcelo d\u2019Amorim and Laurie Williams. 2024. Just another copy and paste? Comparing the security vulnerabilities of ChatGPT generated code and StackOverflow answers. arXiv:https:\/\/arXiv.org\/abs\/2403.15600 (2024).","DOI":"10.1109\/SPW63631.2024.00014"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623175"},{"key":"e_1_3_3_2_21_2","unstructured":"Hamel Husain Ho-Hsiang Wu Tiferet Gazit Miltiadis Allamanis and Marc Brockschmidt. 2019. Codesearchnet challenge: Evaluating the state of semantic code search. arXiv:https:\/\/arXiv.org\/abs\/1909.09436 (2019)."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"J. Li S. Ji T. Du B. Li and T. Wang. 2018. Textbugger: Generating adversarial text against real-world applications. arXiv:https:\/\/arXiv.org\/abs\/1812.05271 (2018).","DOI":"10.14722\/ndss.2019.23138"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Linyang Li Ruotian Ma Qipeng Guo Xiangyang Xue and Xipeng Qiu. 2020. Bert-attack: Adversarial attack against bert using bert. arXiv:https:\/\/arXiv.org\/abs\/2004.09984 (2020).","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"e_1_3_3_2_25_2","unstructured":"Zhuoyan Li Hangxiao Zhu Zhuoran Lu and Ming Yin. 2023. Synthetic data generation with large language models for text classification: Potential and limitations. arXiv:https:\/\/arXiv.org\/abs\/2310.07849 (2023)."},{"key":"e_1_3_3_2_26_2","unstructured":"Yinhan Liu. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv:https:\/\/arXiv.org\/abs\/1907.11692 364 (2019)."},{"key":"e_1_3_3_2_27_2","unstructured":"Shuai Lu Daya Guo Shuo Ren Junjie Huang Alexey Svyatkovskiy Ambrosio Blanco Colin Clement Dawn Drain Daxin Jiang Duyu Tang et\u00a0al. 2021. Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv:https:\/\/arXiv.org\/abs\/2102.04664 (2021)."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639174"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00181"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"John\u00a0X Morris Eli Lifland Jin\u00a0Yong Yoo Jake Grigsby Di Jin and Yanjun Qi. 2020. Textattack: A framework for adversarial attacks data augmentation and adversarial training in nlp. arXiv:https:\/\/arXiv.org\/abs\/2005.05909 (2020).","DOI":"10.18653\/v1\/2020.emnlp-demos.16"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00099"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Arbi\u00a0Haza Nasution and Aytug Onan. 2024. ChatGPT Label: Comparing the Quality of Human-Generated and LLM-Generated Annotations in Low-resource Language NLP Tasks. IEEE Access (2024).","DOI":"10.1109\/ACCESS.2024.3402809"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643991.3644933"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Xipeng Qiu Tianxiang Sun Yige Xu Yunfan Shao Ning Dai and Xuanjing Huang. 2020. Pre-trained models for natural language processing: A survey. Science China Technological Sciences 63 10 (2020) 1872\u20131897.","DOI":"10.1007\/s11431-020-1647-3"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Md\u00a0Shamimur Rahman Zadia Codabux and Chanchal\u00a0K Roy. 2024. Do Words Have Power? Understanding and Fostering Civility in Code Review Discussion. Proceedings of the ACM on Software Engineering 1 FSE (2024) 1632\u20131655.","DOI":"10.1145\/3660780"},{"key":"e_1_3_3_2_36_2","unstructured":"Alexander\u00a0J Ratner Christopher\u00a0M De\u00a0Sa Sen Wu Daniel Selsam and Christopher R\u00e9. 2016. Data programming: Creating large training sets quickly. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"N Reimers. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv:https:\/\/arXiv.org\/abs\/1908.10084 (2019).","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1103"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWSC60764.2023.00011"},{"key":"e_1_3_3_2_40_2","unstructured":"V Sanh. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. arXiv:https:\/\/arXiv.org\/abs\/1910.01108 (2019)."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Jaydeb Sarker Asif\u00a0Kamal Turzo Ming Dong and Amiangshu Bosu. 2023. Automated identification of toxic code reviews using toxicr. ACM Transactions on Software Engineering and Methodology 32 5 (2023) 1\u201332.","DOI":"10.1145\/3583562"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643991.3645071"},{"key":"e_1_3_3_2_43_2","unstructured":"Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna Dumitru Erhan Ian Goodfellow and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv:https:\/\/arXiv.org\/abs\/1312.6199 (2013)."},{"key":"e_1_3_3_2_44_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_45_2","unstructured":"Jiongxiao Wang Zichen Liu Keun\u00a0Hee Park Muhao Chen and Chaowei Xiao. 2023. Adversarial demonstration attacks on large language models. arXiv:https:\/\/arXiv.org\/abs\/2305.14950 (2023)."},{"key":"e_1_3_3_2_46_2","unstructured":"Fangzhou Wu Xiaogeng Liu and Chaowei Xiao. 2023. Deceptprompt: Exploiting llm-driven code generation via adversarial natural language instructions. arXiv:https:\/\/arXiv.org\/abs\/2312.04730 (2023)."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510146"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534390"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5469"}],"event":{"name":"EASE '25: Evaluation and Assessment in Software Engineering","location":"Istanbul Turkiye","acronym":"EASE '25"},"container-title":["Proceedings of the 29th International Conference on Evaluation and Assessment in Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3756681.3756985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T08:42:31Z","timestamp":1766565751000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3756681.3756985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":48,"alternative-id":["10.1145\/3756681.3756985","10.1145\/3756681"],"URL":"https:\/\/doi.org\/10.1145\/3756681.3756985","relation":{},"subject":[],"published":{"date-parts":[[2025,6,17]]},"assertion":[{"value":"2025-12-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}