{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T23:34:01Z","timestamp":1722987241864},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Sci. Eng."],"published-print":{"date-parts":[[2024,3]]},"abstract":"Abstract<\/jats:title>Large language models (LLMs) have shown superior performance in various areas. And LLMs have the potential to revolutionize data management by serving as the \"brain\" of next-generation database systems. However, there are several challenges that utilize LLMs to optimize databases. First, it is challenging to provide appropriate prompts (e.g., instructions and demonstration examples) to enable LLMs to understand the database optimization problems. Second, LLMs only capture the logical database characters (e.g., SQL semantics) but are not aware of physical characters (e.g., data distributions), and it requires to fine-tune LLMs to capture both physical and logical information. Third, LLMs are not well trained for databases with strict constraints (e.g., query plan equivalence) and privacy-preserving requirements, and it is challenging to train database-specific LLMs while ensuring database privacy. To overcome these challenges, this vision paper proposes a LLM-based database framework (), including automatic prompt generation, DB-specific model fine-tuning, and DB-specific model design and pre-training. Preliminary experiments show that achieves relatively good performance in database tasks like query rewrite and index tuning. The source code and datasets are available at github.com\/TsinghuaDatabaseGroup\/DB-GPT.<\/jats:p>","DOI":"10.1007\/s41019-023-00235-6","type":"journal-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T07:02:21Z","timestamp":1705647741000},"page":"102-111","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DB-GPT: Large Language Model Meets Database"],"prefix":"10.1007","volume":"9","author":[{"given":"Xuanhe","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Zhaoyan","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-1398-0621","authenticated-orcid":false,"given":"Guoliang","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,19]]},"reference":[{"key":"235_CR1","first-page":"1877","volume":"2020","author":"B Brown Tom","year":"2020","unstructured":"Brown Tom B et al (2020) Language models are few-shot learners. Adv Neural Inf Proc Syst 2020:1877\u20131901","journal-title":"Advances in neural information processing systems"},{"issue":"3","key":"235_CR2","first-page":"100","volume":"2022","author":"J Liu","year":"2022","unstructured":"Liu J, Shen D, Zhang Y, Dolan B, Carin L, Chen W (2022) What Makes Good In-Context Examples for GPT-3? DeeLIO 2022(3):100\u2013114","journal-title":"DeeLIO"},{"issue":"4","key":"235_CR3","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","volume":"30","author":"L Floridi","year":"2020","unstructured":"Floridi L, Chiriatti M (2020) GPT-3: its nature, scope, limits, and consequences. Minds Mach 30(4):681\u2013694","journal-title":"Minds Mach"},{"key":"235_CR4","doi-asserted-by":"crossref","unstructured":"Svyatkovskiy A, Deng S K, Fu S, Sundaresan N (2020) Intellicode compose: code generation using transformer. In: FSE, pp 1433\u20131443","DOI":"10.1145\/3368089.3417058"},{"issue":"3","key":"235_CR5","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1109\/TKDE.2020.2994641","volume":"34","author":"X Zhou","year":"2022","unstructured":"Zhou X, Chai C, Li G, Sun J (2022) Database meets artificial intelligence: a survey. IEEE Trans Knowl Data Eng 34(3):1096\u20131116","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"235_CR6","doi-asserted-by":"crossref","unstructured":"Li G, Zhou X, Cao L (2021) AI meets database: AI4DB and DB4AI. In: SIGMOD \u201921: International conference on management of data, virtual event, China, Jun 20-25. ACM, pp 2859\u20132866","DOI":"10.1145\/3448016.3457542"},{"key":"235_CR7","doi-asserted-by":"crossref","unstructured":"Zhang X, Wu H, Chang Z, Jin S, Tan J, Li F, Zhang T, Cui B (2021) restune: resource oriented tuning boosted by meta-learning for cloud databases. In: SIGMOD \u201921: International conference on management of data, virtual event, China, Jun 20-25. ACM, pp 2102\u20132114","DOI":"10.1145\/3448016.3457291"},{"key":"235_CR8","unstructured":"Dong Q, Li L, Dai D, Zheng C, Wu Z, Chang B, Sun X, Xu J, Li L, Sui Z (2022) A survey for in-context learning. arXiv preprint arXiv:2301.00234"},{"key":"235_CR9","doi-asserted-by":"crossref","unstructured":"Sorensen Taylor et\u00a0al (2022) An information-theoretic approach to prompt engineering without ground truth labels. In: Proceedings of the 60th annual meeting of the association for computational linguistics, vol\u00a01. Association for computational linguistics, Stroudsburg, pp 819\u2013862","DOI":"10.18653\/v1\/2022.acl-long.60"},{"key":"235_CR10","unstructured":"Zhou Y, Muresanu A I, Han Z, Paster K, Pitis S, Chan H, Ba J (2022) Large language models are human-level prompt engineers. In: The Eleventh International Conference on Learning Representations"},{"key":"235_CR11","doi-asserted-by":"crossref","unstructured":"Honovich O, Shaham S\u00a0R B, Omer L (2022) instruction induction: from few examples to natural language task descriptions, pp 1\u201317","DOI":"10.18653\/v1\/2023.acl-long.108"},{"key":"235_CR12","unstructured":"Razeghi Y, Logan R\u00a0L, Wallace E, Singh S (2020) AUTOPROMPT : eliciting knowledge from language models with automatically generated prompts, pp 4222\u20134235"},{"key":"235_CR13","unstructured":"Yao L, Bartolo M, Moore A, Riedel S, Stenetorp P (2022) Fantastically ordered prompts and where to find them: overcoming few-shot prompt order sensitivity. 1:8086\u20138098"},{"key":"235_CR14","unstructured":"Zhao T Z, Wallace E, Feng S, Klein D, Singh S (2021) Calibrate before use: improving few-shot performance of language models. In International Conference on Machine Learning, pp 12697\u201312706"},{"key":"235_CR15","unstructured":"Fu Y, Peng H, Sabharwal A, Clark P, Khot T (2022) Complexity-based prompting for multi-step reasoning, pp 1\u201314"},{"key":"235_CR16","unstructured":"Kim H\u00a0J, Cho H, Kim J, Kim T, Yoo K\u00a0M, Lee S-G (2022) Self-generated in-context learning: leveraging auto-regressive language models as a demonstration generator"},{"key":"235_CR17","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei J, Wang X, Schuurmans D, Bosma M, Ichter B, Xia F, Chi E, Le Q, Zhou D (2022) Chain-of-thought prompting elicits reasoning in large language models. Adv Neural Inf Proc Syst 35:24824\u201324837","journal-title":"Advances in Neural Information Processing Systems"},{"key":"235_CR18","doi-asserted-by":"crossref","unstructured":"Press O, Zhang M, Min S, Schmidt L, Smith N\u00a0A, Lewis M (2022) Measuring and narrowing the compositionality gap in language models, pp 1\u201325","DOI":"10.18653\/v1\/2023.findings-emnlp.378"},{"key":"235_CR19","unstructured":"Zhou D, Sch\u00e4rli N, Hou L, Wei J, Scales N, Wang X, Schuurmans D, Cui C, Bousquet O, Le Q, Chi E (2022) Least-to-most prompting enables complex reasoning in large language models"},{"key":"235_CR20","doi-asserted-by":"crossref","unstructured":"Zhang Y, Feng S, Tan C (2022) Active example selection for in-context learning","DOI":"10.18653\/v1\/2022.emnlp-main.622"},{"key":"235_CR21","unstructured":"Wang X, Zhu W, Wang William Y (2023) Large language models are implicitly topic models: explaining and finding good demonstrations for in-context learning. arXiv preprint arXiv:2301.11916"},{"key":"235_CR22","unstructured":"Wu Z, Wang Y, Ye J, Kong L Self-adaptive in-context learning. arXiv preprint arXiv:2212.10375"},{"key":"235_CR23","unstructured":"Shao Z, Gong Y, Shen Y, Huang M, Duan N, Chen W (2023) Synthetic prompting: generating chain-of-thought demonstrations for large language models"},{"key":"235_CR24","doi-asserted-by":"crossref","unstructured":"Rubin O, Herzig J, Berant J (2022) Learning to retrieve prompts for in-context learning. In: NAACL 2022 - 2022 Conference of the north American chapter of the association for computational linguistics: human language technologies, proceedings of the conference, pp 2655\u20132671","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"235_CR25","doi-asserted-by":"crossref","unstructured":"Levy I, Bogin B, Berant J (2022) Diverse demonstrations improve in-context compositional generalization","DOI":"10.18653\/v1\/2023.acl-long.78"},{"key":"235_CR26","doi-asserted-by":"crossref","unstructured":"Magister L C, Mallinson J , Adamek J , Malmi E, Severyn A (2022) Teaching small language models to reason. arXiv preprint arXiv:2212.08410","DOI":"10.18653\/v1\/2023.acl-short.151"},{"key":"235_CR27","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C L, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, Schulman J, Hilton J, Kelton F, Miller L, Simens M, Askell A, Welinder P, Christiano P, Leike J, Lowe R (2022) Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730\u201327744","journal-title":"Advances in Neural Information Processing Systems"},{"key":"235_CR28","doi-asserted-by":"crossref","unstructured":"Ding N, Qin Y, Yang G, Wei F et\u00a0al (2022) Delta tuning: a comprehensive study of parameter efficient methods for pre-trained language models. CoRR, arXiv:abs\/2203.06904","DOI":"10.21203\/rs.3.rs-1553541\/v1"},{"key":"235_CR29","unstructured":"Liu X, Zheng Y, Du Z, Ding M, Qian Y, Yang Z, Tang J (2021) GPT understands, too. AI Open"},{"key":"235_CR30","doi-asserted-by":"crossref","unstructured":"Yang Z, Liang E, Kamsetty A, Wu C, Duan Y, Chen X, Abbeel P, Hellerstein JM, Krishnan S, Stoica I, Berkeley UC (2019) Deep unsupervised cardinality estimation, vol \u00a013","DOI":"10.14778\/3368289.3368294"},{"issue":"6","key":"235_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3460427","volume":"54","author":"X Yin","year":"2021","unstructured":"Yin X, Zhu Y, Hu J (2021) A comprehensive survey of privacy-preserving federated learning: a taxonomy, review, and future directions. ACM Comput Surv 54(6):1","journal-title":"ACM Comput Surv"},{"key":"235_CR32","unstructured":"Liu R, Wei J, Gu S\u00a0S, Wu T-Y, Vosoughi S, Cui C, Zhou D, Dai A\u00a0M (2022) Mind\u2019s eye: grounded language model reasoning through simulation, pp 1\u201318"},{"key":"235_CR33","doi-asserted-by":"crossref","unstructured":"Liu J, Liu A, Ximing L, Welleck S, West P, Le Bras R, Choi Y, Hajishirzi H (2022) Generated knowledge prompting for commonsense reasoning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (volume 1: Long Papers), pp 3154\u20133169","DOI":"10.18653\/v1\/2022.acl-long.225"},{"key":"235_CR34","unstructured":"Creswell A, Shanahan M (2022) Faithful reasoning using large language models. Number, pp 1\u201348"},{"key":"235_CR35","unstructured":"https:\/\/platform.openai.com\/docs\/models\/gpt-3-5"},{"key":"235_CR36","doi-asserted-by":"crossref","unstructured":"Yang Z, Kamsetty A, Luan S, Liang E, Duan Y, Chen X, Stoica I (2020) Neurocard: one cardinality estimator for all tables. In: Proceedings of the VLDB endowment, vol 14, pp 61\u201373","DOI":"10.14778\/3421424.3421432"},{"key":"235_CR37","volume-title":"Methods and experimental results","author":"W Bin","year":"2019","unstructured":"Bin W, Angela W, Fenxiao C, Wang Yuncheng C (2019) Methods and experimental results. C. Jay Kuo, Evaluating word embedding models"},{"key":"235_CR38","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","volume":"1","author":"J Zhou","year":"2020","unstructured":"Zhou J, Cui G, Shengding H, Zhang Z, Yang C, Liu Z, Wang L, Li C, Sun M (2020) Graph neural networks: a review of methods and applications. AI open 1:57\u201381","journal-title":"AI open"},{"issue":"9","key":"235_CR39","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.14778\/3397230.3397238","volume":"13","author":"X Zhou","year":"2020","unstructured":"Zhou X, Sun J, Li G, Feng J (2020) Query performance prediction for concurrent queries using graph embedding. Proc VLDB Endow 13(9):1416\u20131428","journal-title":"Proc VLDB Endow"},{"key":"235_CR40","first-page":"632","volume":"2022","author":"S Wiegreffe","year":"2022","unstructured":"Wiegreffe S, Hessel J, Swayamdipta S, Riedl M, Choi Y (2022) Reframing human-AI collaboration for generating free-text explanations. NAACL 2022:632\u2013658","journal-title":"NAACL"},{"key":"235_CR41","unstructured":"Houlsby N, Giurgiu A, Jastrz\u00e7bski S, Morrone B, Laroussilhe Q de, Gesmundo A, Attariyan M, Gelly S (2019) Parameter-efficient transfer learning for NLP. In: 36th International conference on machine learning, ICML 2019, 2019 Jun, pp 4944\u20134953"},{"key":"235_CR42","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Shean W L, W, and Weizhu C (2021) LoRA: low-rank adaptation of large language models. 10:1\u201326"},{"key":"235_CR43","first-page":"337","volume-title":"ETAPS","author":"L De Moura","year":"2008","unstructured":"De Moura L, Bj\u00f8rner N (2008) Z3: An efficient smt solver. ETAPS. Springer, Cham, pp 337\u2013340"},{"key":"235_CR44","doi-asserted-by":"crossref","unstructured":"Kraska T, Beutel A, Chi E\u00a0H, Dean J, Polyzotis N (2018) The case for learned index structures. In: Proceedings of the 2018 international conference on management of data, pp 489\u2013504","DOI":"10.1145\/3183713.3196909"},{"key":"235_CR45","unstructured":"Mitzenmacher M (2018) A model for learned bloom filters and related structures. arXiv preprint arXiv:1802.00884,"},{"key":"235_CR46","unstructured":"Sun Y, Wang S, Feng S, Ding S, Pang C, Shang J, Liu J, Chen X, Zhao Y, Yuxiang L, Liu W, Zhihua W, Gong W, Liang J, Shang Z, Sun P, Liu W, Ouyang X, Dianhai Y, Tian H, Hua W, Wang H (2021) Ernie 3.0: large-scale knowledge enhanced pre-training for language understanding and generation"},{"key":"235_CR47","unstructured":"Zhang S, Roller S , Goyal N, Artetxe M, Chen M, Chen S, Dewan C, Diab M, Li X, Lin XV, Mihaylov T, Ott M, Shleifer S, Shuster K, Simig D, Koura PS, Sridhar A, Wang T, Zettlemoyer L (2022) OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068"},{"key":"235_CR48","unstructured":"Zeng A, Liu X, Zhengxiao D, Wang Z, Lai H, Ding M, Yang Z, Yifan X, Zheng W, Xia X, Tam WL, Ma Z, Xue Y, Zhai J, Chen W, Zhang P, Dong Y, Tang J (2022) GLM-130B: an open bilingual pre-trained model. 06"},{"key":"235_CR49","unstructured":"Chowdhery A et\u00a0al (2022) Palm: scaling language modeling with pathways"},{"key":"235_CR50","unstructured":"Han J, Rong Y, Xu T, Huang W (2022) Geometrically equivariant graph neural networks: a survey. arXiv preprint arXiv:2202.07230"},{"key":"235_CR51","unstructured":"Wu Y, Rabe M\u00a0N, Hutchins D, Szegedy C (2022) Memorizing transformers, pp 1\u201319"},{"issue":"6","key":"235_CR52","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou J, Baosheng Yu, Maybank SJ, Tao D (2021) Knowledge distillation: a survey. Int J Comput Vision 129(6):1789\u20131819","journal-title":"Int J Comput Vision"},{"issue":"10","key":"235_CR53","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1007\/s11431-020-1647-3","volume":"63","author":"XP Qiu","year":"2020","unstructured":"Qiu XP, Sun TX, YiGe X, Shao YF, Dai N, Huang XJ (2020) Pre-trained models for natural language processing: A survey. Sci Chin Technol Sci 63(10):1872\u20131897","journal-title":"Sci Chin Technol Sci"},{"issue":"1","key":"235_CR54","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.csl.2014.09.005","volume":"30","author":"W De Mulder","year":"2015","unstructured":"De Mulder W, Bethard S, Moens M-F (2015) A survey on the application of recurrent neural networks to statistical language modeling. Comput Speech Language 30(1):61\u201398","journal-title":"Comput Speech Language"},{"key":"235_CR55","doi-asserted-by":"crossref","unstructured":"Li J, Tang T, Zhao W\u00a0X, Wen J-R (2021) Pretrained language models for text generation: A survey. arXiv preprint arXiv:2105.10311,","DOI":"10.24963\/ijcai.2021\/612"},{"key":"235_CR56","unstructured":"Jing K, Xu J (2019) A survey on neural network language models. arXiv preprint arXiv:1906.03591"},{"key":"235_CR57","doi-asserted-by":"crossref","unstructured":"Pengfei L, Weizhe Y, Jinlan F, Zhengbao J, Hiroaki H, Graham N (2023) Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing 55:1\u201335","DOI":"10.1145\/3560815"},{"key":"235_CR58","unstructured":"Devlin Jacob, Chang Ming-Wei, Lee Kenton, Toutanova Kristina (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT, pp 4171\u20134186"},{"key":"235_CR59","doi-asserted-by":"crossref","unstructured":"Zhang Z, Han X, Liu Z, Jiang X, Sun M, Liu Q (2020) ErniE: Enhanced language representation with informative entities. ACL, pp 1441\u20131451","DOI":"10.18653\/v1\/P19-1139"},{"key":"235_CR60","doi-asserted-by":"crossref","unstructured":"Trummer I (2022) DB-BERT: a database tuning tool that \"reads the manual\u201d. In: SIGMOD, pp 190\u2013203","DOI":"10.1145\/3514221.3517843"},{"issue":"11","key":"235_CR61","doi-asserted-by":"publisher","first-page":"2921","DOI":"10.14778\/3551793.3551841","volume":"15","author":"I Trummer","year":"2022","unstructured":"Trummer I (2022) Codexdb: synthesizing code for query processing from natural language instructions using GPT-3 codex. Proc VLDB Endow 15(11):2921\u20132928","journal-title":"Proc VLDB Endow"}],"container-title":["Data Science and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41019-023-00235-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41019-023-00235-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41019-023-00235-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T15:21:47Z","timestamp":1711725707000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41019-023-00235-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":61,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["235"],"URL":"https:\/\/doi.org\/10.1007\/s41019-023-00235-6","relation":{},"ISSN":["2364-1185","2364-1541"],"issn-type":[{"value":"2364-1185","type":"print"},{"value":"2364-1541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,19]]},"assertion":[{"value":"6 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interest"}}]}}