{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:06:35Z","timestamp":1779131195000,"version":"3.51.4"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2023YFB4503600"],"award-info":[{"award-number":["2023YFB4503600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSF of China","doi-asserted-by":"crossref","award":["62525202, 62232009"],"award-info":[{"award-number":["62525202, 62232009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2026,5,18]]},"abstract":"<jats:p>Large language models (LLMs) have revolutionized the semantic processing of unstructured data, unlocking new avenues for data analytics beyond traditional relational databases. However, optimizing query execution over unstructured data requires accurate semantic cardinality estimation, a problem that remains unsolved due to the absence of schemas and the high cost of semantic judgments. In this paper, we present SemStats, a framework that efficiently and accurately estimates the number of results for semantic queries. SemStats first constructs a semantic catalog that identifies core semantic dimensions and their relationships within the corpus. Based on the catalog, SemStats then builds a semantic index that constructs the relationships between data points and semantic catalog. As it is expensive to assess the relationships between data points and catalog using LLMs, we propose specialized lightweight models to improve index-construction cost. For online estimation, SemStats employs stratified importance sampling guided by the semantic index and a lightweight judge model to refine query-specific evaluations. Experiments on multiple real-world datasets show that SemStats substantially reduces estimation error (up to 25X) and latency (up to 31X) compared to state-of-the-art baselines, enabling accurate and efficient cardinality estimation of semantic queries on unstructured data.<\/jats:p>","DOI":"10.1145\/3802024","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T18:19:16Z","timestamp":1779128356000},"page":"1-26","source":"Crossref","is-referenced-by-count":0,"title":["Bridging the Gap: Cardinality Estimation for Semantic Queries on Unstructured Data"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2345-8054","authenticated-orcid":false,"given":"Shihui","family":"Xu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9700-9751","authenticated-orcid":false,"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1398-0621","authenticated-orcid":false,"given":"Guoliang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"[n.d.]. Amazon Bedrock Pricing. https:\/\/aws.amazon.com\/cn\/bedrock\/pricing\/?refid=5eef8ffa-5155-4b81-9303--69672b9516c1."},{"key":"e_1_2_1_2_1","unstructured":"[n.d.]. Amazon EC2 Pricing. https:\/\/aws.amazon.com\/cn\/ec2\/."},{"key":"e_1_2_1_3_1","unstructured":"[n.d.]. OpenAI Latency optimization. https:\/\/platform.openai.com\/docs\/guides\/latency-optimization."},{"key":"e_1_2_1_4_1","unstructured":"[n.d.]. Sports stackexchange data. https:\/\/archive.org\/download\/stackexchange\/sports.stackexchange.com.7z."},{"key":"e_1_2_1_5_1","volume-title":"Bohou Li, Mark Lindblad, Henry Lindeman, Alex Meyer, Parth Parmar, Tanvi Ranade, Mehul A Shah, et al.","author":"Anderson Eric","year":"2024","unstructured":"Eric Anderson, Jonathan Fritz, Austin Lee, Bohou Li, Mark Lindblad, Henry Lindeman, Alex Meyer, Parth Parmar, Tanvi Ranade, Mehul A Shah, et al. 2024. The Design of an LLM-powered Unstructured Analytics System. arXiv preprint arXiv:2409.00847 (2024)."},{"key":"e_1_2_1_6_1","volume-title":"Top2Vec: Distributed Representations of Topics. CoRR abs\/2008.09470","author":"Angelov Dimo","year":"2020","unstructured":"Dimo Angelov. 2020. Top2Vec: Distributed Representations of Topics. CoRR abs\/2008.09470 (2020). arXiv:2008.09470 https:\/\/arxiv.org\/abs\/2008.09470"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.FINDINGS-EMNLP.790"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/3626292.3626294"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.ACL-LONG.297"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0927-0507(06)13004-2"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1963405.1963487"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3329772.3329780"},{"key":"e_1_2_1_13_1","volume-title":"Robert Osazuwa Ness, and Jonathan Larson.","author":"Edge Darren","year":"2024","unstructured":"Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitan- sky, Robert Osazuwa Ness, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130 (2024)."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2006.61"},{"key":"e_1_2_1_15_1","unstructured":"Neel Guha Julian Nyarko Daniel E. Ho Christopher R\u00e9 Adam Chilton K. Aditya Alex Chohlas-Wood et al. 2023. LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023 New Orleans LA USA December 10 - 16 2023 Alice Oh Tristan Naumann Amir Globerson Kate Saenko Moritz Hardt and Sergey Levine (Eds.). 147:25"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389741"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.14778\/3384345.3384349"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.FINDINGS-EMNLP.390"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/S11042-018-6894-4"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1108\/00220410410560573"},{"key":"e_1_2_1_21_1","volume-title":"Learned Cardinalities: Estimating Correlated Joins with Deep Learning. In 9th Biennial Conference on Innovative Data Sys- tems Research, CIDR","author":"Kipf Andreas","year":"2019","unstructured":"Andreas Kipf, Thomas Kipf, Bernhard Radke, Viktor Leis, Peter A. Boncz, and Alfons Kemper. 2019. Learned Cardinalities: Estimating Correlated Joins with Deep Learning. In 9th Biennial Conference on Innovative Data Sys- tems Research, CIDR 2019, Asilomar, CA, USA, January 13-16, 2019, Online Proceedings. www.cidrdb.org. http: \/\/cidrdb.org\/cidr2019\/papers\/p101-kipf-cidr19.pdf"},{"key":"e_1_2_1_22_1","unstructured":"Viktor Leis Bernhard Radke Andrey Gubichev Alfons Kemper and Thomas Neumann. 2017. Cardinality Estimation Done Right: Index-Based Join Sampling.. In Cidr."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/3750601.3750619"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3722212.3725641"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.04674"},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the Conference on Innovative Database Research (CIDR).","author":"Liu Chunwei","year":"2025","unstructured":"Chunwei Liu, Matthew Russo, Michael Cafarella, Lei Cao, Peter Baile Chen, Zui Chen, Michael Franklin, Tim Kraska, Samuel Madden, Rana Shahout, et al. 2025. Palimpzest: Optimizing ai-powered analytics with declarative query processing. In Proceedings of the Conference on Innovative Database Research (CIDR)."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685916"},{"key":"e_1_2_1_28_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Merity Stephen","year":"2017","unstructured":"Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2017. Pointer Sentinel Mixture Models. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=Byj72udxe"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2407"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/235968.233342"},{"key":"e_1_2_1_31_1","first-page":"486","article-title":"Selectivity estimation without the attribute value independence assumption","volume":"97","author":"Poosala Viswanath","year":"1997","unstructured":"Viswanath Poosala and Yannis E Ioannidis. 1997. Selectivity estimation without the attribute value independence assumption. In VLDB, Vol. 97. 486-495.","journal-title":"VLDB"},{"key":"e_1_2_1_32_1","unstructured":"PostgreSQL. 2026. PG STATISTICS. https:\/\/www.postgresql.org\/docs\/current\/view-pg-stats.html. PostgreSQL Documentation."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/D19-1410"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/582095.582099"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.14778\/3746405.3746426"},{"key":"e_1_2_1_36_1","unstructured":"SQL Server. 2026. SQL Server STATISTICS. https:\/\/learn.microsoft.com\/en-us\/sql\/relational-databases\/statistics\/ statistics?view=sql-server-ver17. SQL Server Documentation."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368296"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.06515"},{"key":"e_1_2_1_39_1","volume-title":"Data agent: A holistic architecture for orchestrating data ai ecosystems. arXiv preprint arXiv:2507.01599","author":"Sun Zhaoyan","year":"2025","unstructured":"Zhaoyan Sun, Jiayi Wang, Xinyang Zhao, Jiachi Wang, and Guoliang Li. 2025. Data agent: A holistic architecture for orchestrating data ai ecosystems. arXiv preprint arXiv:2507.01599 (2025)."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/3750601.3750625"},{"key":"e_1_2_1_41_1","volume-title":"Federated Data Analytics with Differentially Private Density Estimation Model. In 2025 IEEE 41st International Conference on Data Engineering (ICDE). IEEE, 2768-2781","author":"Wang Jiayi","year":"2025","unstructured":"Jiayi Wang, Lei Cao, Chengliang Chai, and Guoliang Li. 2025. Federated Data Analytics with Differentially Private Density Estimation Model. In 2025 IEEE 41st International Conference on Data Engineering (ICDE). IEEE, 2768-2781."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/3485450.3485458"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/S00778-023-00808-X"},{"key":"e_1_2_1_44_1","volume-title":"Unify: An Unstructured Data Analytics System. In 2025 IEEE 41st International Conference on Data Engineering (ICDE). IEEE Computer Society, 4662-4674","author":"Wang Jiayi","year":"2025","unstructured":"Jiayi Wang and Jianhua Feng. 2025. Unify: An Unstructured Data Analytics System. In 2025 IEEE 41st International Conference on Data Engineering (ICDE). IEEE Computer Society, 4662-4674."},{"key":"e_1_2_1_45_1","volume-title":"AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries. In CIDR","author":"Wang Jiayi","year":"2025","unstructured":"Jiayi Wang and Guoliang Li. 2025. AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries. In CIDR 2025."},{"key":"e_1_2_1_46_1","unstructured":"Jiayi Wang Guoliang Li and Jianhua Feng. [n.d.]. iDataLake: An LLM-Powered Analytics System on Data Lakes. Data Engineering ([n.d.]) 57."},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.14778\/3750601.3750653"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.14778\/3421424.3421432"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368294"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183739"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/S41019-023-00235-6"},{"key":"e_1_2_1_52_1","volume-title":"Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions. In (ICML 2003)","author":"Zhu Xiaojin","year":"2003","unstructured":"Xiaojin Zhu, Zoubin Ghahramani, and John D. Lafferty. 2003. Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions. In (ICML 2003), August 21-24, 2003, Washington, DC, USA. 912-919."}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3802024","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T18:26:29Z","timestamp":1779128789000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3802024"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,18]]}},"alternative-id":["10.1145\/3802024"],"URL":"https:\/\/doi.org\/10.1145\/3802024","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]}}}