{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T02:10:38Z","timestamp":1784167838811,"version":"3.55.0"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T00:00:00Z","timestamp":1745798400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGMOD Rec."],"published-print":{"date-parts":[[2025,4,28]]},"abstract":"<jats:p>Selecting appropriate values for the configurable knobs of Database Management Systems (DBMS) is essential to improve performance. But because the complexity of this task has surpassed the abilities of even the best human experts, the database community turns to machine learning (ML)- based automatic tuning systems. However, these systems still incur significant tuning costs or only yield suboptimal performance, attributable to their overly high reliance on black-box optimization and the lack of integration with domain knowledge, such as DBMS manuals and forum discussions. Hence, we propose GPTuner, a manual-reading database tuning system that extensively leverages domain knowledge to automatically optimize the search space and enhance the runtime feedback-based optimization process. Firstly, we develop a Large Language Model (LLM)-based pipeline to collect and refine heterogeneous knowledge, and propose a prompt ensemble algorithm to unify a structured view of the refined knowledge. Secondly, using the structured knowledge, we (1) design a workload-aware, trainingfree knob selection strategy, (2) develop a search space optimization technique considering the value range of each knob, (3) propose a Coarse-to-Fine Bayesian Optimization Framework to explore the optimized space. Finally, we evaluate GPTuner under different benchmarks (TPC-C and TPC-H), metrics (throughput and latency) and DBMS (PostgreSQL and MySQL). Compared to state-of-the-art methods, GPTuner identifies better configurations in 16x less time on average. Moreover, GPTuner achieves up to 30% performance improvement over the best-performing alternative.<\/jats:p>","DOI":"10.1145\/3733620.3733641","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T16:20:07Z","timestamp":1745943607000},"page":"101-110","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["GPTuner: An LLM-Based Database Tuning System"],"prefix":"10.1145","volume":"54","author":[{"given":"Jiale","family":"Lao","sequence":"first","affiliation":[{"name":"Sichuan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibo","family":"Wang","sequence":"additional","affiliation":[{"name":"Sichuan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufei","family":"Li","sequence":"additional","affiliation":[{"name":"Sichuan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianping","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwest Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunjia","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanghu","family":"Chen","sequence":"additional","affiliation":[{"name":"Northwest Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingjie","family":"Tang","sequence":"additional","affiliation":[{"name":"Sichuan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianguo","family":"Wang","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"PostgresqlCO.NF. https:\/\/postgresqlco.nf\/."},{"key":"e_1_2_1_2_1","unstructured":"https:\/\/drive.google.com\/file\/d\/ 1Ss6EL-B3lhKkwVNBW5vPu-JQ-IeldaUJ."},{"key":"e_1_2_1_3_1","unstructured":"HackerNews 2021. https:\/\/news.ycombinator.com\/item?id=28869509."},{"key":"e_1_2_1_4_1","unstructured":"2023. https:\/\/www.postgresql.org\/docs\/current\/ runtime-config-resource.html."},{"key":"e_1_2_1_5_1","unstructured":"PostgreSQL 2023. https: \/\/www.postgresql.org\/docs\/current\/index.html."},{"key":"e_1_2_1_6_1","unstructured":"EDB 2023. https:\/\/www.enterprisedb.com\/blog\/ tuning-maxwalsize-postgresql."},{"key":"e_1_2_1_7_1","volume-title":"full version","year":"2024","unstructured":"GPTuner: full version, 2024. https:\/\/github.com\/SolidLao\/GPTuner\/blob\/main\/ gptuner-technical-report.pdf."},{"key":"e_1_2_1_8_1","volume-title":"Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering, ASE '22","author":"Ahmed Toufique","year":"2023","unstructured":"Toufique Ahmed and Premkumar Devanbu. Few-shot training llms for project-specific code-summarization. In Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering, ASE '22, New York, NY, USA, 2023. Association for Computing Machinery."},{"key":"e_1_2_1_9_1","volume-title":"From large language models to databases and back: A discussion on research and education","author":"Amer-Yahia Sihem","year":"2023","unstructured":"Sihem Amer-Yahia, Angela Bonifati, Lei Chen, Guoliang Li, Kyuseok Shim, Jianliang Xu, and Xiaochun Yang. From large language models to databases and back: A discussion on research and education, 2023."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"e_1_2_1_11_1","volume-title":"Ask me anything: A simple strategy for prompting language models","author":"Arora Simran","year":"2022","unstructured":"Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, and Christopher R\u00b4e. Ask me anything: A simple strategy for prompting language models, 2022."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517882"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/3457390.3457404"},{"key":"e_1_2_1_14_1","volume-title":"Binding language models in symbolic languages","author":"Cheng Zhoujun","year":"2023","unstructured":"Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Caiming Xiong, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, and Tao Yu. Binding language models in symbolic languages, 2023."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/1287369.1287454"},{"key":"e_1_2_1_16_1","volume-title":"Dom-lm: Learning generalizable representations for html documents. arXiv preprint arXiv:2201.10608","author":"Deng Xiang","year":"2022","unstructured":"Xiang Deng, Prashant Shiralkar, Colin Lockard, Binxuan Huang, and Huan Sun. Dom-lm: Learning generalizable representations for html documents. arXiv preprint arXiv:2201.10608, 2022."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732240.2732246"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687767"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_1"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488733.3488749"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551844"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380591"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/3659437.3659449"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3654739"},{"key":"e_1_2_1_25_1","volume-title":"On the advance of making language models better reasoners. arXiv preprint arXiv:2206.02336","author":"Li Yifei","year":"2022","unstructured":"Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. On the advance of making language models better reasoners. arXiv preprint arXiv:2206.02336, 2022."},{"issue":"54","key":"e_1_2_1_26_1","first-page":"1","article-title":"A versatile bayesian optimization package for hyperparameter optimization","volume":"23","author":"Lindauer Marius","year":"2022","unstructured":"Marius Lindauer, Katharina Eggensperger, Matthias Feurer, Andr\u00b4e Biedenkapp, Difan Deng, Carolin Benjamins, Tim Ruhkopf, Ren\u00b4e Sass, and Frank Hutter. Smac3: A versatile bayesian optimization package for hyperparameter optimization. Journal of Machine Learning Research, 23(54):1--9, 2022.","journal-title":"Journal of Machine Learning Research"},{"issue":"54","key":"e_1_2_1_27_1","first-page":"1","article-title":"A versatile bayesian optimization package for hyperparameter optimization","volume":"23","author":"Lindauer Marius","year":"2022","unstructured":"Marius Lindauer, Katharina Eggensperger, Matthias Feurer, Andr\u00b4e Biedenkapp, Difan Deng, Carolin Benjamins, Tim Ruhkopf, Ren\u00b4e Sass, and Frank Hutter. Smac3: A versatile bayesian optimization package for hyperparameter optimization. Journal of Machine Learning Research, 23(54):1--9, 2022.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_1_28_1","volume-title":"Chatgpt as a factual inconsistency evaluator for text summarization","author":"Luo Zheheng","year":"2023","unstructured":"Zheheng Luo, Qianqian Xie, and Sophia Ananiadou. Chatgpt as a factual inconsistency evaluator for text summarization, 2023."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/167293.167637"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352116"},{"key":"e_1_2_1_31_1","volume-title":"Gpt-4 technical report. arXiv preprint arXiv:2303.08774","author":"AI.","year":"2023","unstructured":"OpenAI. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023."},{"key":"e_1_2_1_32_1","first-page":"1","volume-title":"CIDR","volume":"4","author":"Pavlo Andrew","year":"2017","unstructured":"Andrew Pavlo, Gustavo Angulo, Joy Arulraj, Haibin Lin, Jiexi Lin, Lin Ma, Prashanth Menon, Todd C Mowry, Matthew Perron, Ian Quah, et al. Self-driving database management systems. In CIDR, volume 4, page 1, 2017."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476411"},{"key":"e_1_2_1_34_1","first-page":"1310","volume-title":"Proceedings of the VLDB Endowment International Conference on Very Large Data Bases","volume":"8","author":"Shin Jaeho","unstructured":"Jaeho Shin, Sen Wu, Feiran Wang, Christopher De Sa, Ce Zhang, and Christopher R\u00b4e. Incremental knowledge base construction using deepdive. In Proceedings of the VLDB Endowment International Conference on Very Large Data Bases, volume 8, page 1310. NIH Public Access, 2015."},{"key":"e_1_2_1_35_1","volume-title":"Practical bayesian optimization of machine learning algorithms. Advances in neural information processing systems, 25","author":"Snoek Jasper","year":"2012","unstructured":"Jasper Snoek, Hugo Larochelle, and Ryan P Adams. Practical bayesian optimization of machine learning algorithms. Advances in neural information processing systems, 25, 2012."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1005686.1005739"},{"key":"e_1_2_1_37_1","volume-title":"Can deep neural networks predict data correlations from column names? arXiv preprint arXiv:2107.04553","author":"Trummer Immanuel","year":"2021","unstructured":"Immanuel Trummer. Can deep neural networks predict data correlations from column names? arXiv preprint arXiv:2107.04553, 2021."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517843"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611630"},{"key":"e_1_2_1_40_1","volume-title":"Skinnerdb: Regret-bounded query evaluation via reinforcement learning. ACM Trans. Database Syst., 46(3), sep","author":"Trummer Immanuel","year":"2021","unstructured":"Immanuel Trummer, Junxiong Wang, Ziyun Wei, Deepak Maram, Samuel Moseley, Saehan Jo, Joseph Antonakakis, and Ankush Rayabhari. Skinnerdb: Regret-bounded query evaluation via reinforcement learning. ACM Trans. Database Syst., 46(3), sep 2021."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064029"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/3450980.3450992"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300085"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/3538598.3538604"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457291"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526176"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00123"},{"key":"e_1_2_1_48_1","volume-title":"Reactable: Enhancing react for table question answering","author":"Zhang Yunjia","year":"2023","unstructured":"Yunjia Zhang, Jordan Henkel, Avrilia Floratou, Joyce Cahoon, Shaleen Deep, and Jignesh M. Patel. Reactable: Enhancing react for table question answering, 2023."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3128605"}],"container-title":["ACM SIGMOD Record"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3733620.3733641","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3733620.3733641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:56:55Z","timestamp":1750298215000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3733620.3733641"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,28]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,4,28]]}},"alternative-id":["10.1145\/3733620.3733641"],"URL":"https:\/\/doi.org\/10.1145\/3733620.3733641","relation":{},"ISSN":["0163-5808"],"issn-type":[{"value":"0163-5808","type":"print"}],"subject":[],"published":{"date-parts":[[2025,4,28]]},"assertion":[{"value":"2025-04-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}