LLM-Driven Database Administration and Natural Language Query Interfaces
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V7I1P165Keywords:
Large Language Models, Database Administration, Natural Language Interfaces, SQL Generation, Autonomous Databases, AI-driven Query Optimization, Intelligent DBAsAbstract
The advent of Large Language Models (LLMs) has transformed multiple domains, including natural language processing, knowledge retrieval, and intelligent automation. In database administration (DBA), LLMs offer unprecedented opportunities to improve efficiency, reduce human error, and enhance accessibility by enabling natural language query interfaces. This paper explores the integration of LLMs into database management systems (DBMS), focusing on their capability to interpret natural language queries, generate complex Structured Query Language (SQL) statements, optimize queries, and autonomously execute administrative tasks. We present a comprehensive methodology for leveraging LLMs as intelligent DBAs, covering query translation, schema understanding, performance optimization, and security enforcement. Furthermore, we examine performance metrics, accuracy evaluations, and user satisfaction through comparative experiments with conventional SQL query interfaces. Our results demonstrate that LLM-driven DBAs significantly reduce query formulation time, increase accessibility for non-technical users, and improve overall database performance while maintaining security compliance. The paper concludes with insights into potential challenges, ethical considerations, and future directions for autonomous database management systems enhanced by LLM technologies.
References
[1] Singh, A., Shetty, A., Ehtesham, A., Kumar, S., & Khoei, T. T. (2025, January). A survey of large language model-based generative ai for text-to-sql: Benchmarks, applications, use cases, and challenges. In 2025 IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC) (pp. 00015-00021). IEEE.
[2] Yu, T., Zhang, R., Yang, K., Yasunaga, M., Wang, D., Li, Z., ... & Radev, D. (2018). Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. arXiv preprint arXiv:1809.08887.
[3] Zhu, C., Lin, Y., Cai, Y., & Li, Y. (2025). SCoT2S: Self-correcting Text-to-SQL parsing by leveraging LLMs. Computer Speech & Language, 101865.
[4] Lin, M., Zhang, H., Lao, J., Li, R., Zhou, Y., Yang, C., ... & Tang, M. (2025). Are your llm-based text-to-sql models secure? exploring sql injection via backdoor attacks. Proceedings of the ACM on Management of Data, 3(6), 1-27.
[5] Peng, X., Zhang, Y., Yang, J., & Stevenson, M. (2022). On the security vulnerabilities of text-to-sql models. arXiv preprint arXiv:2211.15363.
[6] Rahman, P., & Mehnaz, S. (2024). International Journal for Multidisciplinary Research (IJFMR). International Journal for Multidisciplinary Research (IJFMR)(November 01, 2024).
[7] Martinez, O., & Sharma, D. (2023). International Journal on Advanced Computer Theory and Engineering. International Journal on Advanced Computer Theory and Engineering, 12(1), 22-28.
[8] Ahmed, T., Bird, C., Devanbu, P., & Chakraborty, S. (2024). Studying llm performance on closed-and open-source data. arXiv preprint arXiv:2402.15100.
[9] Shi, J., Xu, B., Liang, J., Xiao, Y., Chen, J., Xie, C., ... & Wang, W. (2025, January). Gen-SQL: Efficient Text-to-SQL by bridging natural language question and database schema with pseudo-schema. In Proceedings of the 31st International Conference on Computational Linguistics (pp. 3794-3807).
[10] Liu, R., Chen, X., Zhang, J., Zhang, Q., Zhang, Y., & Yang, B. (2025). SAFENLIDB: A Privacy-Preserving Safety Alignment Framework for LLM-based Natural Language Database Interfaces. arXiv preprint arXiv:2511.06778.
[11] Tedeschi, M., Rizwan, S., Shringi, C., Chandgir, V. D., & Belich, S. (2025). An advanced AI driven database system. arXiv preprint arXiv:2507.17778.
[12] Neumann, A. T., Yin, Y., Sowe, S., Decker, S., & Jarke, M. (2024). An llm-driven chatbot in higher education for databases and information systems. IEEE Transactions on Education.
[13] Nihalani, N., Silakari, S., & Motwani, M. (2011). Natural language interface for database: a brief review. International Journal of Computer Science Issues (IJCSI), 8(2), 600.
[14] Quamar, A., Efthymiou, V., Lei, C., & Özcan, F. (2022). Natural language interfaces to data. Foundations and Trends® in Databases, 11(4), 319-414.
[15] Li, F., & Jagadish, H. V. (2014, June). NaLIR: an interactive natural language interface for querying relational databases. In Proceedings of the 2014 ACM SIGMOD international conference on Management of data (pp. 709-712).
[16] Affolter, K., Stockinger, K., & Bernstein, A. (2019). A comparative survey of recent natural language interfaces for databases. The VLDB Journal, 28(5), 793-819.
[17] Liu, M., & Xu, J. (2025). Nli4db: A systematic review of natural language interfaces for databases. arXiv preprint arXiv:2503.02435.
[18] Fernandez, R. C., Elmore, A. J., Franklin, M. J., Krishnan, S., & Tan, C. (2023). How large language models will disrupt data management. Proceedings of the VLDB Endowment, 16(11), 3302-3309.
[19] Karanikolas, N., Manga, E., Samaridi, N., Tousidou, E., & Vassilakopoulos, M. (2023, November). Large language models versus natural language understanding and generation. In Proceedings of the 27th Pan-Hellenic Conference on Progress in Computing and Informatics (pp. 278-290).
[20] Solanki, A., & Kumar, A. (2022). A system to transform natural language queries into SQL queries. International journal of information technology, 14(1), 437-446.
