{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T16:00:32Z","timestamp":1785340832079,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3794763.3794803","type":"proceedings-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:18:58Z","timestamp":1785338338000},"page":"110-122","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SQL-Commenter: Aligning Large Language Models for SQL Comment Generation with Direct Preference Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3134-3746","authenticated-orcid":false,"given":"Lei","family":"Yu","sequence":"first","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5232-7027","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5475-3815","authenticated-orcid":false,"given":"Jingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5391-8821","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0143-1707","authenticated-orcid":false,"given":"Jia","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8364-6525","authenticated-orcid":false,"given":"Li","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1728-7085","authenticated-orcid":false,"given":"Changzhi","family":"Deng","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6028-4186","authenticated-orcid":false,"given":"Jiajia","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3830-8786","authenticated-orcid":false,"given":"Fengjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,29]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Kamel Alrashedy and Ahmed Binjahlan. 2023. Language Models are Better Bug Detector Through Code-Pair Classification. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.07957 (2023)."},{"key":"e_1_3_3_1_3_2","unstructured":"Zheng Cai Maosong Cao Haojiong Chen Kai Chen Keyu Chen Xin Chen Xun Chen Zehui Chen Zhi Chen Pei Chu et\u00a0al. 2024. Internlm2 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.17297 (2024)."},{"key":"e_1_3_3_1_4_2","first-page":"2541","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Cao Ruisheng","year":"2021","unstructured":"Ruisheng Cao, Lu Chen, Zhi Chen, Yanbin Zhao, Su Zhu, and Kai Yu. 2021. LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2541\u20132555."},{"key":"e_1_3_3_1_5_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde De\u00a0Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et\u00a0al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.03374 (2021)."},{"key":"e_1_3_3_1_6_2","volume-title":"ACL","author":"Chen Rui","year":"2020","unstructured":"Rui Chen and et al.2020. Bridging Text and Schema with Schema-Aware Query Generation. In ACL."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1109\/ISSRE66568.2025.00038","volume-title":"2025 IEEE 36th International Symposium on Software Reliability Engineering (ISSRE)","author":"Cheng Shiqi","year":"2025","unstructured":"Shiqi Cheng, Chenjie Shen, Li Yang, Lei Yu, Fengjun Zhang, and Chun Zuo. 2025. AUVANA: An Efficient and Automatic Approach to Variable Rename Refactoring via Large Pre-trained Language Model. In 2025 IEEE 36th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 288\u2013299."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Ju Fan Zihui Gu Songyue Zhang Yuxin Zhang Zui Chen Lei Cao Guoliang Li Samuel Madden Xiaoyong Du and Nan Tang. 2024. Combining small language models and large language models for zero-shot NL2SQL. Proceedings of the VLDB Endowment 17 11 (2024) 2750\u20132763.","DOI":"10.14778\/3681954.3681960"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3608134"},{"key":"e_1_3_3_1_10_2","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et\u00a0al. 2024. The llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_1_11_2","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et\u00a0al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.12948 (2025)."},{"key":"e_1_3_3_1_12_2","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Yu Wu YK Li et\u00a0al. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming\u2013The Rise of Code Intelligence. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.14196 (2024)."},{"key":"e_1_3_3_1_13_2","first-page":"4524","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Guo Jiaqi","year":"2019","unstructured":"Jiaqi Guo, Zecheng Zhan, Yan Gao, Yan Xiao, Jian-Guang Lou, Ting Liu, and Dongmei Zhang. 2019. Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 4524\u20134535."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Zijin Hong Zheng Yuan Qinggang Zhang Hao Chen Junnan Dong Feiran Huang and Xiao Huang. 2025. Next-generation database interfaces: A survey of llm-based text-to-sql. IEEE Transactions on Knowledge and Data Engineering (2025).","DOI":"10.1109\/TKDE.2025.3609486"},{"key":"e_1_3_3_1_15_2","volume-title":"Findings of ACL","author":"Huang Xinya","year":"2023","unstructured":"Xinya Huang and et al.2023. GenerationSQL: Enhancing In-Context Examples for Text-to-SQL. In Findings of ACL."},{"key":"e_1_3_3_1_16_2","unstructured":"Binyuan Hui Jian Yang Zeyu Cui Jiaxi Yang Dayiheng Liu Lei Zhang Tianyu Liu Jiajun Zhang Bowen Yu Keming Lu et\u00a0al. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.12186 (2024)."},{"key":"e_1_3_3_1_17_2","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Kocetkov Denis","year":"2022","unstructured":"Denis Kocetkov, Raymond Li, Loubna\u00a0Ben Allal, Leandro\u00a0von Werra, Chenghao Mou, Sean Hughes, Arjun Guha, Sasha Luccioni, Yacine Jernite, and Thomas Wolf. 2022. The stack: 3 tb of permissively licensed source code. In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_3_1_18_2","volume-title":"VLDB","author":"Li Fei","year":"2014","unstructured":"Fei Li and H.\u00a0V. Jagadish. 2014. Constructing a semantic parser from a domain ontology. In VLDB."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Jinyang Li Binyuan Hui Ge Qu Jiaxi Yang Binhua Li Bowen Li Bailin Wang Bowen Qin Ruiying Geng Nan Huo et\u00a0al. 2023. Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls. Advances in Neural Information Processing Systems 36 (2023) 42330\u201342357.","DOI":"10.52202\/075280-1835"},{"key":"e_1_3_3_1_20_2","unstructured":"Raymond Li Loubna\u00a0Ben Allal Yangtian Zi Niklas Muennighoff Denis Kocetkov Chenghao Mou Marc Marone Christopher Akiki Jia Li Jenny Chim et\u00a0al. 2023. Starcoder: may the source be with you! arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.06161 (2023)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549081"},{"key":"e_1_3_3_1_22_2","first-page":"74","volume-title":"Text summarization branches out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74\u201381."},{"key":"e_1_3_3_1_23_2","unstructured":"Aiwei Liu Xuming Hu Lijie Wen and Philip\u00a0S Yu. 2023. A comprehensive evaluation of ChatGPT\u2019s zero-shot Text-to-SQL capability. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.13547 (2023)."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Jiawei Liu Chunqiu\u00a0Steven Xia Yuyao Wang and Lingming Zhang. 2023. Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation. Advances in Neural Information Processing Systems 36 (2023) 21558\u201321572.","DOI":"10.52202\/075280-0943"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-90900-9_3"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00026"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Da Ma Xingyu Chen Ruisheng Cao Zhi Chen Lu Chen and Kai Yu. 2021. Relation-aware graph transformer for sql-to-text generation. Applied Sciences 12 1 (2021) 369.","DOI":"10.3390\/app12010369"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387467"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Mohammadreza Pourreza and Davood Rafiei. 2023. Din-sql: Decomposed in-context learning of text-to-sql with self-correction. Advances in Neural Information Processing Systems 36 (2023) 36339\u201336348.","DOI":"10.52202\/075280-1577"},{"key":"e_1_3_3_1_30_2","unstructured":"Quora. 2025. Can you explain why SQL queries can be difficult? https:\/\/www.quora.com\/. Accessed on October 19 2025."},{"key":"e_1_3_3_1_31_2","unstructured":"Nitarshan Rajkumar Raymond Li and Dzmitry Bahdanau. 2022. Evaluating the text-to-sql capabilities of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.00498 (2022)."},{"key":"e_1_3_3_1_32_2","unstructured":"Baptiste Roziere Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing\u00a0Ellen Tan Yossi Adi Jingyu Liu Romain Sauvestre Tal Remez et\u00a0al. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.12950 (2023)."},{"key":"e_1_3_3_1_33_2","first-page":"311","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Rubin Ohad","year":"2021","unstructured":"Ohad Rubin and Jonathan Berant. 2021. SmBoP: Semi-autoregressive Bottom-up Semantic Parsing. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 311\u2013324."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.779"},{"key":"e_1_3_3_1_35_2","first-page":"1","volume-title":"2024 International Joint Conference on Neural Networks (IJCNN)","author":"Shen Chenjie","year":"2024","unstructured":"Chenjie Shen, Jie Zhu, Lei Yu, Li Yang, and Chun Zuo. 2024. Dependency-Aware Method Naming Framework with Generative Adversarial Sampling. In 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Chang Shu Yusen Zhang Xiangyu Dong Peng Shi Tao Yu and Rui Zhang. 2021. Logic-consistency text generation from semantic parses. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.00577 (2021).","DOI":"10.18653\/v1\/2021.findings-acl.388"},{"key":"e_1_3_3_1_37_2","unstructured":"Stack Overflow. 2023. 2023 Developer Survey. https:\/\/survey.stackoverflow.co\/2023\/. Accessed on October 19 2025."},{"key":"e_1_3_3_1_38_2","unstructured":"Stack Overflow. 2025. Newest \u2019sql\u2019 Questions. https:\/\/stackoverflow.com\/questions\/tagged\/sql. Accessed on October 19 2025. The page listed 674 654 questions with the \"sql\" tag.."},{"key":"e_1_3_3_1_39_2","first-page":"13843","volume-title":"Proceedings of the AAAI conference on artificial intelligence","volume":"35","author":"Stoica George","year":"2021","unstructured":"George Stoica, Emmanouil\u00a0Antonios Platanios, and Barnab\u00e1s P\u00f3czos. 2021. Re-tacred: Addressing shortcomings of the tacred dataset. In Proceedings of the AAAI conference on artificial intelligence , Vol.\u00a035. 13843\u201313850."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1109\/ISSRE66568.2025.00033","volume-title":"2025 IEEE 36th International Symposium on Software Reliability Engineering (ISSRE)","author":"Tang Jiayue","year":"2025","unstructured":"Jiayue Tang, Li Yang, Lei Yu, Junyi Lu, Zhirong Huang, Fengjun Zhang, and Chun Zuo. 2025. Breaking Task Isolation: Enhancing Code Review Automation with Mixture-of-Experts Large Language Models. In 2025 IEEE 36th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 227\u2013238."},{"key":"e_1_3_3_1_41_2","unstructured":"InternLM Team. 2023. Internlm: A multilingual language model with progressively enhanced capabilities."},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Stephen Thomas Laurie Williams and Tao Xie. 2009. On automated prepared statement generation to remove SQL injection vulnerabilities. Information and Software technology 51 3 (2009) 589\u2013598.","DOI":"10.1016\/j.infsof.2008.08.002"},{"key":"e_1_3_3_1_43_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519665"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.677"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Martin Weyssow Xin Zhou Kisub Kim David Lo and Houari Sahraoui. 2025. Exploring parameter-efficient fine-tuning techniques for code generation with large language models. ACM Transactions on Software Engineering and Methodology 34 7 (2025) 1\u201325.","DOI":"10.1145\/3714461"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Kun Xu Lingfei Wu Zhiguo Wang Yansong Feng and Vadim Sheinin. 2018. Sql-to-text generation with graph-to-sequence model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1809.05255 (2018).","DOI":"10.18653\/v1\/D18-1112"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1112"},{"key":"e_1_3_3_1_49_2","first-page":"1299","volume-title":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","author":"Yan Cong","year":"2017","unstructured":"Cong Yan, Alvin Cheung, Junwen Yang, and Shan Lu. 2017. Understanding database performance inefficiencies in real-world web applications. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. 1299\u20131308."},{"key":"e_1_3_3_1_50_2","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et\u00a0al. 2025. Qwen3 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.09388 (2025)."},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1041"},{"key":"e_1_3_3_1_52_2","unstructured":"Lei Yu Shiqi Chen Hang Yuan Peng Wang Zhirong Huang Jingyuan Zhang Chenjie Shen Fengjun Zhang Li Yang and Jiajia Ma. 2024. Smart-LLaMA: Two-Stage Post-Training of Large Language Models for Smart Contract Vulnerability Detection and Explanation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.06221 (2024)."},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Lei Yu Shiqi Cheng Zhirong Huang Jingyuan Zhang Chenjie Shen Junyi Lu Li Yang Fengjun Zhang and Jiajia Ma. 2025. Sael: Leveraging large language models with adaptive mixture-of-experts for smart contract vulnerability detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.22371 (2025).","DOI":"10.1109\/ICSME64153.2025.00016"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Lei Yu Zhirong Huang Hang Yuan Shiqi Cheng Li Yang Fengjun Zhang Chenjie Shen Jiajia Ma Jingyuan Zhang Junyi Lu et\u00a0al. 2025. Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection. Proceedings of the ACM on Software Engineering 2 ISSTA (2025) 182\u2013205.","DOI":"10.1145\/3728878"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00030"},{"key":"e_1_3_3_1_56_2","first-page":"1","volume-title":"2023 International Joint Conference on Neural Networks (IJCNN)","author":"Yu Lei","year":"2023","unstructured":"Lei Yu, Fengjun Zhang, Jiajia Ma, Li Yang, Yuanzhe Yang, and Wei Jia. 2023. Who are the money launderers? money laundering detection on blockchain via mutual learning-based graph neural network. In 2023 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138."},{"key":"e_1_3_3_1_57_2","unstructured":"Lei Yu Jingyuan Zhang Xin Wang Jiajia Ma Li Yang and Fengjun Zhang. 2025. Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.09942 (2025)."},{"key":"e_1_3_3_1_58_2","volume-title":"EMNLP","author":"Yu Tao","year":"2023","unstructured":"Tao Yu and et al.2023. GRAPPA: Grammar-Aware Pre-Training for Text-to-SQL Parsing. In EMNLP."},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"Tao Yu Rui Zhang Kai Yang Michihiro Yasunaga Dongxu Wang Zifan Li James Ma Irene Li Qingning Yao Shanelle Roman et\u00a0al. 2018. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1809.08887 (2018).","DOI":"10.18653\/v1\/D18-1425"},{"key":"e_1_3_3_1_60_2","unstructured":"Hang Yuan Lei Yu Zhirong Huang Jingyuan Zhang Junyi Lu Shiqi Cheng Li Yang Fengjun Zhang Jiajia Ma and Chun Zuo. 2025. Mos: Towards effective smart contract vulnerability detection through mixture-of-experts tuning of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.12234 (2025)."},{"key":"e_1_3_3_1_61_2","unstructured":"Daoguang Zan Zhirong Huang Ailun Yu Shaoxin Lin Yifan Shi Wei Liu Dong Chen Zongshuai Qi Hao Yu Lei Yu et\u00a0al. 2024. Swe-bench-java: A github issue resolving benchmark for java. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.14354 (2024)."},{"key":"e_1_3_3_1_62_2","unstructured":"Bin Zhang Yuxiao Ye Guoqing Du Xiaoru Hu Zhishuai Li et\u00a0al. 2024. Benchmarking the Text-to-SQL Capability of Large Language Models: A Comprehensive Evaluation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.02951 (2024)."},{"key":"e_1_3_3_1_63_2","volume-title":"Proceedings of the 2025 Conference on Computational Linguistics (COLING)","author":"Zhang Bin","year":"2025","unstructured":"Bin Zhang, Yuxiao Ye, Guoqing Du, Xiaoru Hu, Zhishuai Li, et\u00a0al. 2025. Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text. In Proceedings of the 2025 Conference on Computational Linguistics (COLING)."},{"key":"e_1_3_3_1_64_2","unstructured":"Bin Zhang Yuxiao Ye Guoqing Du Xiaoru Hu Zhishuai Li Sun Yang Chi\u00a0Harold Liu Rui Zhao Ziyue Li and Hangyu Mao. 2024. Benchmarking the text-to-sql capability of large language models: A comprehensive evaluation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.02951 (2024)."},{"key":"e_1_3_3_1_65_2","unstructured":"Ge Zhang Scott Qu Jiaheng Liu Chenchen Zhang Chenghua Lin Chou\u00a0Leuang Yu Danny Pan Esther Cheng Jie Liu Qunshu Lin et\u00a0al. 2024. Map-neo: Highly capable and transparent bilingual large language model series. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.19327 (2024)."},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"crossref","unstructured":"Junsan Zhang Ao Lu Junxiao Han Yang Zhu Yudie Yan Juncai Guo and Yao Wan. 2025. HeSQLNet: A Heterogeneous graph neural Network for SQL-to-Text generation. Information and Software Technology (2025) 107820.","DOI":"10.1016\/j.infsof.2025.107820"},{"key":"e_1_3_3_1_67_2","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems","author":"Zhang Jingyuan","unstructured":"Jingyuan Zhang, Xin Wang, Lei Yu, Zhirong Huang, Li Yang, and Fengjun Zhang. [n. d.]. Restricted Global-Aware Graph Filters Bridging GNNs and Transformer for Node Classification. In The Thirty-ninth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"crossref","unstructured":"Jingyuan Zhang Lei Yu Zhirong Huang Li Yang and Fengjun Zhang. 2025. Topology augmented multi-band and multi-scale filtering for graph anomaly detection. ACM Transactions on Knowledge Discovery from Data 19 8 (2025) 1\u201327.","DOI":"10.1145\/3748727"},{"key":"e_1_3_3_1_69_2","unstructured":"Tianyi Zhang Varsha Kishore Felix Wu Kilian\u00a0Q Weinberger and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1904.09675 (2019)."},{"key":"e_1_3_3_1_70_2","unstructured":"Yaowei Zheng Richong Zhang Junhao Zhang Yanhan Ye and Zheyan Luo. 2024. Llamafactory: Unified efficient fine-tuning of 100+ language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.13372 (2024)."},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"crossref","first-page":"396","DOI":"10.18653\/v1\/2020.emnlp-main.29","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Zhong Ruiqi","year":"2020","unstructured":"Ruiqi Zhong, Tao Yu, and Dan Klein. 2020. Semantic evaluation for text-to-SQL with distilled test suites. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 396\u2013411."},{"key":"e_1_3_3_1_72_2","volume-title":"ACL","author":"Zhong Victor","year":"2017","unstructured":"Victor Zhong, Caiming Xiong, and Richard Socher. 2017. Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning. In ACL."},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.77"}],"event":{"name":"ICPC '26: 34th IEEE\/ACM International Conference on Program Comprehension","location":"Rio de Janeiro , Brazil","acronym":"ICPC '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2026 34th IEEE\/ACM International Conference on Program Comprehension"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3794763.3794803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:20:53Z","timestamp":1785338453000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3794763.3794803"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":72,"alternative-id":["10.1145\/3794763.3794803","10.1145\/3794763"],"URL":"https:\/\/doi.org\/10.1145\/3794763.3794803","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}