{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T17:10:31Z","timestamp":1784913031837,"version":"3.55.0"},"reference-count":33,"publisher":"Association for Computing Machinery (ACM)","issue":"12","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2024,8]]},"abstract":"<jats:p>Machine learning techniques have been verified to be effective in optimizing data management systems and are widely researched in recent years. However, traditional small-sized ML models often struggle to generalize to new scenarios, and have limited context understanding ability (e.g., inputting discrete features only). The emergence of LLMs offers a promising solution to these challenges. LLMs have been trained over a vast number of scenarios and tasks and acquire human-competitive capabilities like context understanding and summarization, which can be highly beneficial for data management tasks (e.g., natural language based data analytics). In this tutorial, we present how to utilize LLMs to optimize data management systems and review new techniques for addressing these technical challenges, including hallucination of LLMs, high cost of interacting with LLMs, and low accuracy for processing complicated tasks. First, we discuss retrieval augmented generation (RAG) techniques to address the hallucination problem. Second, we present vector database techniques to improve the latency. Third, we present LLM agent techniques for processing complicated tasks by generating multi-round pipelines. We also showcase some real-world data management scenarios that can be well optimized by LLMs, including query rewrite, database diagnosis and data analytics. Finally, we summarize some open research challenges.<\/jats:p>","DOI":"10.14778\/3685800.3685838","type":"journal-article","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T17:25:21Z","timestamp":1731086721000},"page":"4213-4216","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["LLM for Data Management"],"prefix":"10.14778","volume":"17","author":[{"given":"Guoliang","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanhe","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"A survey on data selection for language models. CoRR, abs\/2402.16827","author":"Albalak A.","year":"2024","unstructured":"A. Albalak, Y. Elazar, S. M. Xie, and et al. A survey on data selection for language models. CoRR, abs\/2402.16827, 2024."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611479.3611497"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2972543"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3654686"},{"key":"e_1_2_1_5_1","volume-title":"et al. Awesome chatgpt prompts. https:\/\/github.com\/f\/awesome-chatgpt-prompts","author":"F. K.","year":"2023","unstructured":"F. K. A. et al. Awesome chatgpt prompts. https:\/\/github.com\/f\/awesome-chatgpt-prompts, 2023."},{"key":"e_1_2_1_6_1","volume-title":"ACM Comput. Surv.","author":"P.","year":"2023","unstructured":"P. L. et al. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Comput. Surv., 2023."},{"key":"e_1_2_1_7_1","volume-title":"Cost-effective in-context learning for entity resolution: A design space exploration. CoRR, abs\/2312.03987","author":"Fan M.","year":"2023","unstructured":"M. Fan, X. Han, J. Fan, C. Chai, N. Tang, G. Li, and X. Du. Cost-effective in-context learning for entity resolution: A design space exploration. CoRR, abs\/2312.03987, 2023."},{"key":"e_1_2_1_8_1","volume-title":"CoRR","author":"Gao Y.","year":"2023","unstructured":"Y. Gao, Y. Xiong, X. Gao, and et al. Retrieval-augmented generation for large language models: A survey. CoRR, 2023."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/69.273032"},{"key":"e_1_2_1_10_1","volume-title":"Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352","author":"Hong S.","year":"2023","unstructured":"S. Hong, X. Zheng, J. Chen, and et al. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 2023."},{"key":"e_1_2_1_11_1","volume-title":"ICLR. OpenReview.net","author":"Hu E. J.","year":"2022","unstructured":"E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen. Lora: Low-rank adaptation of large language models. In ICLR. OpenReview.net, 2022."},{"key":"e_1_2_1_12_1","volume-title":"Llmtune: Accelerate database knob tuning with large language models. CoRR, abs\/2404.11581","author":"Huang X.","year":"2024","unstructured":"X. Huang, H. Li, J. Zhang, and et al. Llmtune: Accelerate database knob tuning with large language models. CoRR, abs\/2404.11581, 2024."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476405"},{"key":"e_1_2_1_14_1","volume-title":"Can LLM already serve as A database interface? A big bench for large-scale database grounded text-to-sqls. CoRR, abs\/2305.03111","author":"Li J.","year":"2023","unstructured":"J. Li, B. Hui, G. Qu, B. Li, J. Yang, B. Li, B. Wang, B. Qin, R. Cao, R. Geng, N. Huo, X. Zhou, C. Ma, G. Li, K. C. Chang, F. Huang, R. Cheng, and Y. Li. Can LLM already serve as A database interface? A big bench for large-scale database grounded text-to-sqls. CoRR, abs\/2305.03111, 2023."},{"key":"e_1_2_1_15_1","volume-title":"CoRR","author":"Liu B.","year":"2023","unstructured":"B. Liu, C. Chen, C. Liao, and et al. Mftcoder: Boosting code llms with multitask fine-tuning. CoRR, 2023."},{"key":"e_1_2_1_16_1","volume-title":"Query rewriting via large language models. CoRR, abs\/2403.09060","author":"Liu J.","year":"2024","unstructured":"J. Liu and B. Mozafari. Query rewriting via large language models. CoRR, abs\/2403.09060, 2024."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.14778\/3389133.3389136"},{"key":"e_1_2_1_18_1","volume-title":"NeurIPS","author":"Ouyang L.","year":"2022","unstructured":"L. Ouyang, J. Wu, X. Jiang, and et al. Training language models to follow instructions with human feedback. In NeurIPS, 2022."},{"key":"e_1_2_1_19_1","volume-title":"Communicative agents for software development. arXiv preprint arXiv:2307.07924","author":"Qian C.","year":"2023","unstructured":"C. Qian, X. Cong, C. Yang, W. Chen, Y. Su, and et al. Communicative agents for software development. arXiv preprint arXiv:2307.07924, 2023."},{"key":"e_1_2_1_20_1","volume-title":"Toolllm: Facilitating large language models to master 16000+ real-world apis. CoRR, abs\/2307.16789","author":"Qin Y.","year":"2023","unstructured":"Y. Qin, S. Liang, Y. Ye, and et al. Toolllm: Facilitating large language models to master 16000+ real-world apis. CoRR, abs\/2307.16789, 2023."},{"key":"e_1_2_1_21_1","volume-title":"NeurIPS","author":"Schick T.","year":"2023","unstructured":"T. Schick, J. Dwivedi-Yu, R. Dess\u00ec, and et al. Toolformer: Language models can teach themselves to use tools. In NeurIPS, 2023."},{"key":"e_1_2_1_22_1","volume-title":"CoRR","author":"Shinn N.","year":"2023","unstructured":"N. Shinn and et al. Reflexion: an autonomous agent with dynamic memory and self-reflection. CoRR, 2023."},{"key":"e_1_2_1_23_1","volume-title":"Rpt: relational pre-trained transformer is almost all you need towards democratizing data preparation. arXiv preprint arXiv:2012.02469","author":"Tang N.","year":"2020","unstructured":"N. Tang, J. Fan, F. Li, J. Tu, X. Du, G. Li, S. Madden, and M. Ouzzani. Rpt: relational pre-trained transformer is almost all you need towards democratizing data preparation. arXiv preprint arXiv:2012.02469, 2020."},{"key":"e_1_2_1_24_1","first-page":"190","volume-title":"SIGMOD","author":"Trummer I.","year":"2022","unstructured":"I. Trummer. DB-BERT: A database tuning tool that \"reads the manual\". In SIGMOD, pages 190--203, 2022."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3003665.3003669"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526125"},{"key":"e_1_2_1_27_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei J.","year":"2022","unstructured":"J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V. Le, D. Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824--24837, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_28_1","volume-title":"React: Synergizing reasoning and acting in language models","author":"Yao S.","year":"2023","unstructured":"S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao. React: Synergizing reasoning and acting in language models, 2023."},{"issue":"3","key":"e_1_2_1_29_1","first-page":"1096","article-title":"Database meets artificial intelligence: A survey","volume":"34","author":"Zhou X.","year":"2020","unstructured":"X. Zhou, C. Chai, G. Li, and J. Sun. Database meets artificial intelligence: A survey. IEEE TKDE, 34(3):1096--1116, 2020.","journal-title":"IEEE TKDE"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/3485450.3485456"},{"key":"e_1_2_1_31_1","volume-title":"Proc. VLDB Endow.","author":"Zhou X.","year":"2024","unstructured":"X. Zhou, G. Li, Z. Sun, and et al. D-bot: Database diagnosis system using large language models. Proc. VLDB Endow., 2024."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-023-00235-6"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3654692"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3685800.3685838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T05:31:27Z","timestamp":1735623087000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3685800.3685838"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":33,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["10.14778\/3685800.3685838"],"URL":"https:\/\/doi.org\/10.14778\/3685800.3685838","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2024,8]]},"assertion":[{"value":"2024-11-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}