[2603.15970] 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models

Computer Science > Databases arXiv:2603.15970 (cs) [Submitted on 16 Mar 2026 (v1), last revised 30 Mar 2026 (this version, v4)] Title:100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models Authors:Yeounoh Chung, Rushabh Desai, Jian He, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Pushkar Khadilkar, Xianshun Chen, Sam Idicula, Fatma Özcan, Alon Halevy, Yannis Papakonstantinou View a PDF of the paper titled 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models, by Yeounoh Chung and 11 other authors View PDF HTML (experimental) Abstract:Several data warehouse and database providers have recently introduced extensions to SQL called AI Queries, enabling users to specify functions and conditions in SQL that are evaluated by LLMs, thereby broadening significantly the kinds of queries one can express over the combination of structured and unstructured data. LLMs offer remarkable semantic reasoning capabilities, making them an essential tool for complex and nuanced queries that blend structured and unstructured data. While extremely powerful, these AI queries can become prohibitively costly when invoked thousands of times. This paper provides an extensive evaluation of a recent AI query approximation approach that enables low cost analytics and database applications to benefit from AI queries. The approach delivers >100x cost and latency reduction for the semantic filt...