{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T18:12:42Z","timestamp":1778695962112,"version":"3.51.4"},"reference-count":94,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62372071"],"award-info":[{"award-number":["62372071"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Chongqing Technology Innovation and Application Development Project","award":["CSTB2022TIAD-STX0007 and CSTB2023TIAD-STX0025"],"award-info":[{"award-number":["CSTB2022TIAD-STX0007 and CSTB2023TIAD-STX0025"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2023CDJKYJH013"],"award-info":[{"award-number":["2023CDJKYJH013"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>\n                    The growing prominence of deep code models in automating software engineering tasks is undeniable. However, their deployment encounters significant challenges in\n                    <jats:italic toggle=\"yes\">on-the-fly performance enhancement<\/jats:italic>\n                    , which refers to dynamically improving the performance of deep code models during real-time execution. Conventional techniques, such as retraining or fine-tuning, are effective in controlled pre-deployment scenarios but fall short when adapting to on-the-fly adjustments post-deployment. CodeDenoise, a notable on-the-fly performance enhancement technology, leverages uncertainty-based methods to identify misclassified inputs and applies an\n                    <jats:italic toggle=\"yes\">input modification strategy<\/jats:italic>\n                    to rectify classification errors. While effective for classification tasks, this approach is inapplicable to generative tasks due to two key challenges: \u2776 Uncertainty-based methods are unsuitable for identifying\n                    <jats:italic toggle=\"yes\">challenging inputs<\/jats:italic>\n                    , especially in generative tasks with diverse and open-ended outputs.\n                    <jats:italic toggle=\"yes\">Challenging inputs<\/jats:italic>\n                    refers to a class of inputs where, due to the inherent complexity of the task or insufficient context in the input samples, the model struggles to generate high-quality outputs. \u2777 Input modification strategies cannot be applied to generative tasks, as modifying the input can unpredictably affect the entire sequence of generated outputs. These limitations highlight the need for novel techniques that can enhance the generation quality of deep code models in real-time.\n                  <\/jats:p>\n                  <jats:p>\n                    To bridge this gap, we propose\n                    <jats:sc>CodEn<\/jats:sc>\n                    , a framework designed to enhance the generation quality of deployed deep code models through model collaboration and real-time output repair.\n                    <jats:sc>CodEn<\/jats:sc>\n                    employs an ensemble learning approach, integrating multiple generic output quality assessment metrics to identify\n                    <jats:italic toggle=\"yes\">challenging inputs<\/jats:italic>\n                    . By combining these diverse metrics,\n                    <jats:sc>CodEn<\/jats:sc>\n                    overcomes the limitations of uncertainty-based methods, making it effective across various generative tasks. Additionally, we introduce an elaborate on-the-fly repair method for the outputs of\n                    <jats:italic toggle=\"yes\">challenging inputs<\/jats:italic>\n                    , leveraging a Large Language Model (LLM) and a novel dual-prompt strategy. This strategy utilizes both generation and selection-based prompts to provide potential fixes and employs an adaptive mechanism to select the optimal output. Our experiments, conducted on 12 deep code models across three pre-trained code models, three popular code-related generation tasks, and four datasets, demonstrate the effectiveness of\n                    <jats:sc>CodEn<\/jats:sc>\n                    . For example, in the assertion generation task,\n                    <jats:sc>CodEn<\/jats:sc>\n                    enhances the Semantic Accuracy Match (SAM) of baseline models with improvements ranging from 12.14% to 21.65%. In the bug fixing task,\n                    <jats:sc>CodEn<\/jats:sc>\n                    achieves exact match gains ranging from 17.51% to 30.64% on TFix dataset. For the code summarization task,\n                    <jats:sc>CodEn<\/jats:sc>\n                    significantly boosts performance across key metrics: BLEU scores improved by 5.72%\u201311.79%, ROUGE-L by 4.41%\u20137.70%, METEOR by 7.51%\u201312.29%, and CIDEr by 8.09%\u201315.80%. Besides, we conduct experiments of\n                    <jats:sc>CodEn<\/jats:sc>\n                    on different open source LLMs and demonstrate that\n                    <jats:sc>CodEn<\/jats:sc>\n                    can still achieve significant improvements.\n                  <\/jats:p>","DOI":"10.1145\/3765752","type":"journal-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T15:36:30Z","timestamp":1757000190000},"page":"1-40","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["On-the-Fly Generation-Quality Enhancement of Deep Code Models via Model Collaboration"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6013-1369","authenticated-orcid":false,"given":"Weifeng","family":"Sun","sequence":"first","affiliation":[{"name":"School of Big Data &amp; Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8754-2060","authenticated-orcid":false,"given":"Naiqi","family":"Huang","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9538-9121","authenticated-orcid":false,"given":"Meng","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Big Data &amp; Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1981-1626","authenticated-orcid":false,"given":"Zhongxin","family":"Liu","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2204-4648","authenticated-orcid":false,"given":"Hongyan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Big Data &amp; Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4504-6806","authenticated-orcid":false,"given":"Yan","family":"Lei","sequence":"additional","affiliation":[{"name":"School of Big Data &amp; Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4367-7201","authenticated-orcid":false,"given":"David","family":"Lo","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,13]]},"reference":[{"key":"e_1_3_3_2_2","unstructured":"Anonymous GitHub. 2024. On-the-Fly Generation-Quality Enhancement of Deep Code Models via Model Collaboration (CodEn). Retrieved from https:\/\/anonymous.4open.science\/r\/CodeEn-C418\/"},{"key":"e_1_3_3_3_2","unstructured":"Cloud Translation. 2024. Interpretation of Bleu Score. Retrieved from https:\/\/cloud.google.com\/translate\/automl\/docs\/evaluate"},{"key":"e_1_3_3_4_2","unstructured":"PyTorch. 2024. Retrieved from https:\/\/pytorch.org\/"},{"key":"e_1_3_3_5_2","unstructured":"Wasi Uddin Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2020. A transformer-based approach for source code summarization. arXiv:2005.00653. Retrieved from https:\/\/arxiv.org\/abs\/2005.00653"},{"key":"e_1_3_3_6_2","first-page":"27865","article-title":"Self-supervised bug detection and repair","volume":"34","author":"Allamanis Miltiadis","year":"2021","unstructured":"Miltiadis Allamanis, Henry Jackson-Flux, and Marc Brockschmidt. 2021. Self-supervised bug detection and repair. In Advances in Neural Information Processing Systems, Vol. 34, 27865\u201327876.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2013.6624029"},{"key":"e_1_3_3_8_2","unstructured":"Jordan T. Ash Chicheng Zhang Akshay Krishnamurthy John Langford and Alekh Agarwal. 2019. Deep batch active learning by diverse uncertain gradient lower bounds. arXiv:1906.03671. Retrieved from https:\/\/arxiv.org\/abs\/1906.03671"},{"key":"e_1_3_3_9_2","first-page":"65","volume-title":"ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, 65\u201372."},{"key":"e_1_3_3_10_2","unstructured":"Yejin Bang Samuel Cahyawijaya Nayeon Lee Wenliang Dai Dan Su Bryan Wilie Holy Lovenia Ziwei Ji Tiezheng Yu Willy Chung et al. 2023. A multitask multilingual multimodal evaluation of ChatGPT on reasoning hallucination and interactivity. arXiv:2302.04023. Retrieved from https:\/\/arxiv.org\/abs\/2302.04023"},{"key":"e_1_3_3_11_2","first-page":"780","volume-title":"International Conference on Machine Learning","author":"Berabi Berkay","year":"2021","unstructured":"Berkay Berabi, Jingxuan He, Veselin Raychev, and Martin Vechev. 2021. Tfix: Learning to fix coding errors with a text-to-text transformer. In International Conference on Machine Learning. PMLR, 780\u2013791."},{"key":"e_1_3_3_12_2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"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, Amanda Askell, et al. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems, Vol. 33, 1877\u20131901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_13_2","first-page":"30","volume-title":"AAAI Conference on Artificial Intelligence","volume":"35","author":"Bui Nghi D. Q.","year":"2021","unstructured":"Nghi D. Q. Bui, Yijun Yu, and Lingxiao Jiang. 2021. Treecaps: Tree-based capsule networks for source code processing. In AAAI Conference on Artificial Intelligence, Vol. 35, 30\u201338."},{"issue":"2","key":"e_1_3_3_14_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3434280","article-title":"Why my code summarization model does not work: Code comment improvement with category prediction","volume":"30","author":"Chen Qiuyuan","year":"2021","unstructured":"Qiuyuan Chen, Xin Xia, Han Hu, David Lo, and Shanping Li. 2021. Why my code summarization model does not work: Code comment improvement with category prediction. ACM Transactions on Software Engineering and Methodology 30, 2 (2021), 1\u201329.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"issue":"9","key":"e_1_3_3_15_2","first-page":"1943","article-title":"Sequencer: Sequence-to-sequence learning for end-to-end program repair","volume":"47","author":"Chen Zimin","year":"2019","unstructured":"Zimin Chen, Steve Kommrusch, Michele Tufano, Louis-No\u00ebl Pouchet, Denys Poshyvanyk, and Martin Monperrus. 2019. Sequencer: Sequence-to-sequence learning for end-to-end program repair. IEEE Transactions on Software Engineering 47, 9 (2019), 1943\u20131959.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639184"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315806730"},{"key":"e_1_3_3_18_2","volume-title":"International Conference on Learning Representations","author":"Dinella Elizabeth","year":"2020","unstructured":"Elizabeth Dinella, Hanjun Dai, Ziyang Li, Mayur Naik, Le Song, and Ke Wang. 2020. Hoppity: Learning graph transformations to detect and fix bugs in programs. In International Conference on Learning Representations."},{"key":"e_1_3_3_19_2","unstructured":"Qingxiu Dong Lei Li Damai Dai Ce Zheng Jingyuan Ma Rui Li Heming Xia Jingjing Xu Zhiyong Wu Tianyu Liu et al. 2022. A survey on in-context learning. arXiv:2301.00234. Retrieved from https:\/\/arxiv.org\/abs\/2301.00234"},{"key":"e_1_3_3_20_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The Llama 3 herd of models. arXiv:2407.21783. Retrieved from https:\/\/arxiv.org\/abs\/2407.21783"},{"issue":"6","key":"e_1_3_3_21_2","article-title":"Exploring the capabilities of LLMs for code change related tasks","volume":"34","author":"Fan Lishui","year":"2025","unstructured":"Lishui Fan, Jiakun Liu, Zhongxin Liu, David Lo, Xin Xia, and Shanping Li. 2025. Exploring the capabilities of LLMs for code change related tasks. ACM Transactions on Software Engineering and Methodology 34, 6 (2025), 1\u201336.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_3_22_2","first-page":"628","volume-title":"33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","author":"Fan Zhiyu","year":"2024","unstructured":"Zhiyu Fan, Haifeng Ruan, Sergey Mechtaev, and Abhik Roychoudhury. 2024. Oracle-guided program selection from large language models. In 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, 628\u2013640."},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397357"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3632746"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/1642293.1642313"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3522674"},{"key":"e_1_3_3_29_2","unstructured":"Shuzheng Gao Wenxin Mao Cuiyun Gao Li Li Xing Hu Xin Xia and Michael R. Lyu. 2024. Learning in the wild: Towards leveraging unlabeled data for effectively tuning pre-trained code models. arXiv:2401.01060. Retrieved from https:\/\/arxiv.org\/abs\/2401.01060"},{"key":"e_1_3_3_30_2","first-page":"30","volume-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE)","author":"Gao Shuzheng","year":"2023","unstructured":"Shuzheng Gao, Hongyu Zhang, Cuiyun Gao, and Chaozheng Wang. 2023. Keeping pace with ever-increasing data: Towards continual learning of code intelligence models. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 30\u201342."},{"key":"e_1_3_3_31_2","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/SANER53432.2022.00013","volume-title":"2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)","author":"Gong Zi","year":"2022","unstructured":"Zi Gong, Cuiyun Gao, Yasheng Wang, Wenchao Gu, Yun Peng, and Zenglin Xu. 2022. Source code summarization with structural relative position guided transformer. In 2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER). IEEE, 13\u201324."},{"key":"e_1_3_3_32_2","unstructured":"Daya Guo Shuai Lu Nan Duan Yanlin Wang Ming Zhou and Jian Yin. 2022. UniXcoder: Unified cross-modal pre-training for code representation. arXiv:2203.03850. Retrieved from https:\/\/arxiv.org\/abs\/2203.03850"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012487302797"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER56733.2023.00056"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524610.3527909"},{"key":"e_1_3_3_36_2","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. Lora: Low-rank adaptation of large language models. In International Conference on Learning Representations ( ICLR), Vol. 1, 3.","journal-title":"International Conference on Learning Representations ( ICLR)"},{"key":"e_1_3_3_37_2","doi-asserted-by":"crossref","unstructured":"Xing Hu Ge Li Xin Xia David Lo Shuai Lu and Zhi Jin. 2018. Summarizing source code with transferred API knowledge. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI) July 13\u201319 2018 Stockholm Sweden. IJCAI 2269\u20132275.","DOI":"10.24963\/ijcai.2018\/314"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.2016299"},{"key":"e_1_3_3_39_2","first-page":"5131","volume-title":"AAAI Conference on Artificial Intelligence","volume":"37","author":"Joshi Harshit","year":"2023","unstructured":"Harshit Joshi, Jos\u00e9 Cambronero Sanchez, Sumit Gulwani, Vu Le, Gust Verbruggen, and Ivan Radi\u010dek. 2023. Repair is nearly generation: Multilingual program repair with LLMs. In AAAI Conference on Artificial Intelligence, Vol. 37, 5131\u20135140."},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2002.1019480"},{"key":"e_1_3_3_41_2","article-title":"LightGBM: A highly efficient gradient boosting decision tree","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/1081706.1081737"},{"key":"e_1_3_3_43_2","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In the ACL-04 Workshop on Text Summarization Branches Out, 74\u201381.","journal-title":"the ACL-04 Workshop on Text Summarization Branches Out"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_3_45_2","first-page":"2476","volume-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE)","author":"Liu Shangqing","year":"2023","unstructured":"Shangqing Liu, Bozhi Wu, Xiaofei Xie, Guozhu Meng, and Yang Liu. 2023. ContraBERT: Enhancing code pre-trained models via contrastive learning. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 2476\u20132487."},{"key":"e_1_3_3_46_2","first-page":"A1","article-title":"For Impatient Web Users, an Eye Blink Is Just Too Long to Wait","author":"Lohr Steve","year":"2012","unstructured":"Steve Lohr. 2012. For Impatient Web Users, an Eye Blink Is Just Too Long to Wait. The New York Times, A1\u2013L.","journal-title":"The New York Times"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397369"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3183297"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00041"},{"key":"e_1_3_3_50_2","volume-title":"6th International Conference on Learning Representations (ICLR \u201918)","author":"Merity Stephen","year":"2018","unstructured":"Stephen Merity, Nitish Shirish Keskar, and Richard Socher. 2018. Regularizing and optimizing LSTM language models. In 6th International Conference on Learning Representations (ICLR \u201918). OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=SyyGPP0TZ"},{"key":"e_1_3_3_51_2","first-page":"1","volume-title":"37th IEEE\/ACM International Conference on Automated Software Engineering","author":"Mu Fangwen","year":"2022","unstructured":"Fangwen Mu, Xiao Chen, Lin Shi, Song Wang, and Qing Wang. 2022. Automatic comment generation via multi-pass deliberation. In 37th IEEE\/ACM International Conference on Automated Software Engineering, 1\u201312."},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00205"},{"key":"e_1_3_3_53_2","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:2203.13474. Retrieved from https:\/\/arxiv.org\/abs\/2203.13474"},{"key":"e_1_3_3_54_2","unstructured":"Erik Nijkamp Bo Pang Hiroaki Hayashi Lifu Tu Huan Wang Yingbo Zhou Silvio Savarese and Caiming Xiong. 2022. A conversational paradigm for program synthesis. arXiv:2203.13474. Retrieved from https:\/\/arxiv.org\/abs\/2203.13474"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00180"},{"key":"e_1_3_3_56_2","doi-asserted-by":"crossref","unstructured":"Yotam Perlitz Ariel Gera Michal Shmueli-Scheuer Dafna Sheinwald Noam Slonim and Liat Ein-Dor. 2023. Active learning for natural language generation. arXiv:2305.15040. Retrieved from https:\/\/arxiv.org\/abs\/2305.15040","DOI":"10.18653\/v1\/2023.emnlp-main.611"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3276517"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1002\/spe.2921"},{"key":"e_1_3_3_59_2","volume-title":"Introduction to Information Retrieval","author":"Sch\u00fctze Hinrich","year":"2008","unstructured":"Hinrich Sch\u00fctze, Christopher D. Manning, and Prabhakar Raghavan. 2008. Introduction to Information Retrieval, Vol. 39. Cambridge University Press Cambridge."},{"key":"e_1_3_3_60_2","unstructured":"Ozan Sener and Silvio Savarese. 2017. Active learning for convolutional neural networks: A core-set approach. arXiv:1708.00489. Retrieved from https:\/\/arxiv.org\/abs\/1708.00489"},{"key":"e_1_3_3_61_2","unstructured":"Burr Settles. 2009. Active Learning Literature Survey. University of Wisconsin-Madison Department of Computer Sciences."},{"key":"e_1_3_3_62_2","article-title":"On-the-fly adaptation of source code models","author":"Shrivastava Disha","year":"2020","unstructured":"Disha Shrivastava, Hugo Larochelle, and Daniel Tarlow. 2020. On-the-fly adaptation of source code models. In NeurIPS 2020 Workshop on Computer-Assisted Programming.","journal-title":"NeurIPS 2020 Workshop on Computer-Assisted Programming"},{"key":"e_1_3_3_63_2","unstructured":"Weisong Sun Chunrong Fang Yudu You Yun Miao Yi Liu Yuekang Li Gelei Deng Shenghan Huang Yuchen Chen Quanjun Zhang et al. 2023. Automatic code summarization via ChatGPT: How far are we? arXiv:2305.12865. Retrieved from https:\/\/arxiv.org\/abs\/2305.12865"},{"key":"e_1_3_3_64_2","first-page":"1123","volume-title":"2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE)","author":"Sun Weifeng","year":"2023","unstructured":"Weifeng Sun, Hongyan Li, Meng Yan, Yan Lei, and Hongyu Zhang. 2023. Revisiting and improving retrieval-augmented deep assertion generation. In 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 1123\u20131135."},{"key":"e_1_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3330982"},{"key":"e_1_3_3_66_2","volume-title":"An Elementary Mathematical Theory of Classification and Prediction","author":"Tanimoto T. T.","year":"1958","unstructured":"T. T. Tanimoto. 1958. An Elementary Mathematical Theory of Classification and Prediction. International Business Machines Corporation. Retrieved from https:\/\/books.google.com.hk\/books?id=yp34HAAACAAJ"},{"key":"e_1_3_3_67_2","unstructured":"Chris Thunes. 2019. Javalang. Retrieved from https:\/\/github.com\/c2nes\/javalang"},{"key":"e_1_3_3_68_2","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1109\/ASE56229.2023.00166","volume-title":"2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE)","author":"Tian Zhao","year":"2023","unstructured":"Zhao Tian, Junjie Chen, and Xiangyu Zhang. 2023. On-the-fly improving performance of deep code models via input denoising. In 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 560\u2013572."},{"key":"e_1_3_3_69_2","first-page":"1","volume-title":"37th IEEE\/ACM International Conference on Automated Software Engineering","author":"Tian Zhao","year":"2022","unstructured":"Zhao Tian, Junjie Chen, Qihao Zhu, Junjie Yang, and Lingming Zhang. 2022. Learning to construct better mutation faults. In 37th IEEE\/ACM International Conference on Automated Software Engineering, 1\u201313."},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2019.00046"},{"key":"e_1_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340544"},{"key":"e_1_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_3_73_2","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/SANER50967.2021.00032","volume-title":"2021 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)","author":"Wang Bei","year":"2021","unstructured":"Bei Wang, Meng Yan, Zhongxin Liu, Ling Xu, Xin Xia, Xiaohong Zhang, and Dan Yang. 2021. Quality assurance for automated commit message generation. In 2021 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER). IEEE, 260\u2013271."},{"key":"e_1_3_3_74_2","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1109\/ICSE48619.2023.00013","volume-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE)","author":"Wang Deze","year":"2023","unstructured":"Deze Wang, Boxing Chen, Shanshan Li, Wei Luo, Shaoliang Peng, Wei Dong, and Xiangke Liao. 2023. One adapter for all programming languages? Adapter tuning for code search and summarization. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 5\u201316."},{"key":"e_1_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510062"},{"issue":"4","key":"e_1_3_3_76_2","article-title":"Software testing with large language models: Survey, landscape, and vision","volume":"50","author":"Wang Junjie","year":"2024","unstructured":"Junjie Wang, Yuchao Huang, Chunyang Chen, Zhe Liu, Song Wang, and Qing Wang. 2024. Software testing with large language models: Survey, landscape, and vision. IEEE Transactions on Software Engineering 50, 4 (2024), 911\u2013936.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616256"},{"key":"e_1_3_3_78_2","unstructured":"Xin Wang Yasheng Wang Fei Mi Pingyi Zhou Yao Wan Xiao Liu Li Li Hao Wu Jin Liu and Xin Jiang. 2021. Syncobert: Syntax-guided multi-modal contrastive pre-training for code representation. arXiv:2108.04556. Retrieved from https:\/\/arxiv.org\/abs\/2108.04556"},{"key":"e_1_3_3_79_2","doi-asserted-by":"crossref","unstructured":"Yue Wang Weishi Wang Shafiq R. Joty and Steven C. H. Hoi. 2021. CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv:2109.00859. Retrieved from https:\/\/arxiv.org\/abs\/2109.00859","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380429"},{"key":"e_1_3_3_81_2","first-page":"349","volume-title":"35th IEEE\/ACM International Conference on Automated Software Engineering","author":"Wei Bolin","year":"2020","unstructured":"Bolin Wei, Yongmin Li, Ge Li, Xin Xia, and Zhi Jin. 2020. Retrieve and refine: Exemplar-based neural comment generation. In 35th IEEE\/ACM International Conference on Automated Software Engineering, 349\u2013360."},{"key":"e_1_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_16"},{"key":"e_1_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00129"},{"key":"e_1_3_3_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3428230"},{"key":"e_1_3_3_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510149"},{"key":"e_1_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2022.111304"},{"key":"e_1_3_3_87_2","unstructured":"Wojciech Zaremba Ilya Sutskever and Oriol Vinyals. 2014. Recurrent neural network regularization. arXiv:1409.2329. Retrieved from http:\/\/arxiv.org\/abs\/1409.2329"},{"key":"e_1_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511887"},{"key":"e_1_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380383"},{"key":"e_1_3_3_90_2","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/ASE56229.2023.00063","volume-title":"2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE)","author":"Zhang Quanjun","year":"2023","unstructured":"Quanjun Zhang, Chunrong Fang, Tongke Zhang, Bowen Yu, Weisong Sun, and Zhenyu Chen. 2023. Gamma: Revisiting template-based automated program repair via mask prediction. In 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 535\u2013547."},{"key":"e_1_3_3_91_2","unstructured":"Ting Zhang Ivana Clairine Irsan Ferdian Thung David Lo Asankhaya Sharma and Lingxiao Jiang. 2023. Evaluating pre-trained language models for repairing API misuses. arXiv:2310.16390. Retrieved from https:\/\/arxiv.org\/abs\/2310.16390"},{"key":"e_1_3_3_92_2","doi-asserted-by":"crossref","unstructured":"Tianyu Zheng Ge Zhang Tianhao Shen Xueling Liu Bill Yuchen Lin Jie Fu Wenhu Chen and Xiang Yue. 2024. Opencodeinterpreter: Integrating code generation with execution and refinement. arXiv:2402.14658. Retrieved from https:\/\/arxiv.org\/abs\/2402.14658","DOI":"10.18653\/v1\/2024.findings-acl.762"},{"key":"e_1_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"key":"e_1_3_3_94_2","unstructured":"Qihao Zhu Daya Guo Zhihong Shao Dejian Yang Peiyi Wang Runxin Xu Y. Wu Yukun Li Huazuo Gao Shirong Ma et al. 2024. DeepSeek-Coder-V2: Breaking the barrier of closed-source models in code intelligence. arXiv:2406.11931. Retrieved from https:\/\/arxiv.org\/abs\/2406.11931"},{"key":"e_1_3_3_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3631972"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3765752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:26:55Z","timestamp":1778693215000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3765752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,13]]},"references-count":94,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3765752"],"URL":"https:\/\/doi.org\/10.1145\/3765752","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,13]]},"assertion":[{"value":"2024-11-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}