--> 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 filter operator and also important gains for semantic ranking. The cost and performance gains come from utilizing cheap and accurate proxy models over embedding vectors. We show that despite the massive gains in latency and cost, these proxy models preserve accuracy and occasionally improve accuracy across various benchmark datasets, including the extended Amazon reviews benchmark that has 10M rows. We present an OLAP-friendly architecture within Google BigQuery for this approach for purely online (ad hoc) queries, and a low-latency HTAP database-friendly architecture in AlloyDB that could further improve the latency by moving the proxy model training offline. We present techniques that accelerate the proxy model training. Subjects: Databases (cs.DB) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2603.15970 [cs.DB] (or arXiv:2603.15970v4 [cs.DB] for this version) https://doi.org/10.48550/arXiv.2603.15970 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.1145/3802002 Focus to learn more DOI(s) linking to related resources Submission history From: Yeounoh Chung [ view email ] [v1] Mon, 16 Mar 2026 22:42:45 UTC (1,233 KB) [v2] Wed, 18 Mar 2026 17:17:29 UTC (1,233 KB) [v3] Tue, 24 Mar 2026 20:09:39 UTC (1,233 KB) [v4] Mon, 30 Mar 2026 20:02:58 UTC (1,233 KB) Full-text links: Access Paper: 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) TeX Source view license Current browse context: cs.DB < prev | next > new | recent | 2026-03 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation &times; loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) Links to Code Toggle Papers with Code ( What is Papers with Code? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? )