{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:13:57Z","timestamp":1792782837854,"version":"4.5.0"},"reference-count":92,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"The Fundamental Research Funds for the Central Universities, Peking University","id":[{"id":"https:\/\/ror.org\/02v51f717","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s00778-026-00975-7","type":"journal-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T04:27:04Z","timestamp":1784867224000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Can large language models be a cardinality estimator? An empirical study"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2744-3083","authenticated-orcid":false,"given":"Liangzu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinjun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runze","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peizhi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianjun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuxin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tieying","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"key":"975_CR1","unstructured":"Ergastf1 dataset. https:\/\/relational-data.org\/dataset\/ErgastF1"},{"key":"975_CR2","unstructured":"STATS Dataset. https:\/\/relational.fit.cvut.cz\/dataset\/Stats"},{"key":"975_CR3","unstructured":"Visualgenome dataset. https:\/\/relational-data.org\/dataset\/VisualGenome"},{"key":"975_CR4","unstructured":"MySQL 8.0 Reference Manual, 2020. Configuring Non-Persistent Optimizer Statistics Parameters"},{"issue":"6671","key":"975_CR5","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1126\/science.adi6000","volume":"382","author":"AN Angelopoulos","year":"2023","unstructured":"Angelopoulos, A.N., Bates, S., Fannjiang, C., Jordan, M.I., Zrnic, T.: Prediction-powered inference. Science 382(6671), 669\u2013674 (2023)","journal-title":"Science"},{"issue":"6","key":"975_CR6","first-page":"3319","volume":"26","author":"M Aytimur","year":"2018","unstructured":"Aytimur, M., Cakmak, A.: Estimating the selectivity of like queries using pattern-based histograms. Turk. J. Electr. Eng. Comput. Sci. 26(6), 3319\u20133334 (2018)","journal-title":"Turk. J. Electr. Eng. Comput. Sci."},{"issue":"1","key":"975_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3639309","volume":"2","author":"M Aytimur","year":"2024","unstructured":"Aytimur, M., Reiner, S., W\u00f6rteler, L., Chondrogiannis, T., Grossniklaus, M.: Lplm: A neural language model for cardinality estimation of like-queries. Proc. ACM Manage. Data 2(1), 1\u201325 (2024)","journal-title":"Proc. ACM Manage. Data"},{"key":"975_CR8","unstructured":"Chaudhuri, S., Ganti, V., Gravano, L.: Selectivity estimation for string predicates: Overcoming the underestimation problem. In Proceedings. 20th International Conference on Data Engineering, pp. 227\u2013238. IEEE, (2004)"},{"key":"975_CR9","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., De Oliveira Pinto, H. P., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G. et al. Evaluating large language models trained on code. (2021). arXiv preprint arXiv:2107.03374"},{"key":"975_CR10","unstructured":"The dblp team. dblp computer science bibliography, 2019. Monthly snapshot release of November (2019)"},{"key":"975_CR11","unstructured":"DeepSeek-AI. Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model, (2024)"},{"key":"975_CR12","unstructured":"Dixon, P. M.: Bootstrap resampling. Encyclopedia Environ. (2006)"},{"key":"975_CR13","unstructured":"Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Yang, A., Fan, A. et al. The llama 3 herd of models. (2024). arXiv preprint arXiv:2407.21783"},{"issue":"11","key":"975_CR14","doi-asserted-by":"publisher","first-page":"2750","DOI":"10.14778\/3681954.3681960","volume":"17","author":"J Fan","year":"2024","unstructured":"Fan, J., Gu, Z., Zhang, S., Zhang, Y., Chen, Z., Cao, L., Li, G., Madden, S., Du, X., Tang, N.: Combining small language models and large language models for zero-shot nl2sql. Proc. VLDB Endow. 17(11), 2750\u20132763 (2024)","journal-title":"Proc. VLDB Endow."},{"key":"975_CR15","volume-title":"Database systems: the complete book","author":"H Garcia-Molina","year":"2008","unstructured":"Garcia-Molina, H.: Database systems: the complete book. Pearson Education India (2008)"},{"key":"975_CR16","doi-asserted-by":"crossref","unstructured":"Gekhman, Z., Yona, G., Aharoni, R., Eyal, M., Feder, A., Reichart, R., Herzig, J.: Does fine-tuning llms on new knowledge encourage hallucinations? (2024). arXiv preprint arXiv:2405.05904","DOI":"10.18653\/v1\/2024.emnlp-main.444"},{"key":"975_CR17","unstructured":"PostgreSQL Global Development Group. Postgresql. https:\/\/www.postgresql.org, 1996. Accessed: 2022-10-28"},{"issue":"4","key":"975_CR18","doi-asserted-by":"publisher","first-page":"752","DOI":"10.14778\/3503585.3503586","volume":"15","author":"Y Han","year":"2021","unstructured":"Han, Y., Wu, Z., Wu, P., Zhu, R., Yang, J., Tan, L.W., Zeng, K., Cong, G., Qin, Y., Pfadler, A., et al.: Cardinality estimation in dbms: a comprehensive benchmark evaluation. Proc. VLDB Endow. 15(4), 752\u2013765 (2021)","journal-title":"Proc. VLDB Endow."},{"key":"975_CR19","unstructured":"Hayek, R., Shmueli, O.: Nn-based transformation of any sql cardinality estimator for handling distinct, and, or and not. (2020). arXiv preprint arXiv:2004.07009"},{"key":"975_CR20","doi-asserted-by":"crossref","unstructured":"Heimel, M., Kiefer, M., Markl, V.: Self-tuning, gpu-accelerated kernel density models for multidimensional selectivity estimation. In Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, pp. 1477\u20131492 (2015)","DOI":"10.1145\/2723372.2749438"},{"key":"975_CR21","doi-asserted-by":"crossref","unstructured":"Hilprecht, B., Schmidt, A., Kulessa, M., Molina, A., Kersting, K., Binnig, C.: Deepdb: Learn from data, not from queries! Proceedings of the VLDB Endowment, 13(7)","DOI":"10.14778\/3384345.3384349"},{"key":"975_CR22","doi-asserted-by":"crossref","unstructured":"Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., de Las Casas, D., Hendricks, L. A., Welbl, J., Clark, A., et al. Training compute-optimal large language models. In Proceedings of the 36th International Conference on Neural Information Processing Systems, pp. 30016\u201330030, (2022)","DOI":"10.52202\/068431-2176"},{"key":"975_CR23","unstructured":"Hu, E. J., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., et al. Lora: Low-rank adaptation of large language models. In International Conference on Learning Representations"},{"key":"975_CR24","unstructured":"Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. (2023). arXiv preprint arXiv:2311.05232"},{"key":"975_CR25","unstructured":"Huang, X., Li, H., Zhang, J., Zhao, X., Yao, Z., Li, Y., Yu, Z.: Tieying Zhang, Hong Chen, and Cuiping Li. Llmtune: Accelerate database knob tuning with large language models. (2024). arXiv preprint arXiv:2404.11581"},{"key":"975_CR26","doi-asserted-by":"crossref","unstructured":"Jagadish, H.V., Ng, R. T., Srivastava, D.: Substring selectivity estimation. In Proceedings of the eighteenth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems, pp. 249\u2013260 (1999)","DOI":"10.1145\/303976.304001"},{"key":"975_CR27","unstructured":"Job-light Workload. Job-light workload. https:\/\/github.com\/andreaskipf\/learnedcardinalities\/blob\/master\/workloads\/job-light.sql. Accessed: 2024-10-13"},{"key":"975_CR28","unstructured":"Kang, F., Just, H. A., Sun, Y., Jahagirdar, H., Zhang, Y., Du, R., Sahu, A. K., Jia, R.: Get more for less: Principled data selection for warming up fine-tuning in llms. In The Twelfth International Conference on Learning Representations"},{"key":"975_CR29","doi-asserted-by":"crossref","unstructured":"Kim, K., Jung, J., Seo, I., Han, W.-S., Choi, K., Chong, J.: Learned cardinality estimation: An in-depth study. In Proceedings of the 2022 international conference on management of data, pp. 1214\u20131227, (2022)","DOI":"10.1145\/3514221.3526154"},{"issue":"1","key":"975_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3639300","volume":"2","author":"K Kim","year":"2024","unstructured":"Kim, K., Lee, S., Kim, I., Han, W.-S.: Asm: Harmonizing autoregressive model, sampling, and multi-dimensional statistics merging for cardinality estimation. Proc. ACM Manage. Data 2(1), 1\u201327 (2024)","journal-title":"Proc. ACM Manage. Data"},{"key":"975_CR31","unstructured":"Kipf, A., Freitag, M., Vorona, D., Boncz, P., Neumann, T., Kemper, A.: Estimating filtered group-by queries is hard: Deep learning to the rescue. In 1st International Workshop on Applied AI for Database Systems and Applications, (2019)"},{"key":"975_CR32","unstructured":"Kipf, A., Kipf, T., Radke, B., Leis, V., Boncz, P., Kemper, A.: Learned cardinalities: Estimating correlated joins with deep learning"},{"key":"975_CR33","doi-asserted-by":"crossref","unstructured":"Krishnan, P., Vitter, J. S., Iyer, B.: Estimating alphanumeric selectivity in the presence of wildcards. In Proceedings of the 1996 ACM SIGMOD international conference on Management of data, pp. \u2013293, (1996)","DOI":"10.1145\/233269.233341"},{"issue":"1","key":"975_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3588713","volume":"1","author":"M Kurmanji","year":"2023","unstructured":"Kurmanji, M., Triantafillou, P.: Detect, distill and update: Learned db systems facing out of distribution data. Proc. ACM Manage. Data 1(1), 1\u201327 (2023)","journal-title":"Proc. ACM Manage. Data"},{"issue":"11","key":"975_CR35","doi-asserted-by":"publisher","first-page":"3145","DOI":"10.14778\/3551793.3551859","volume":"15","author":"S Kwon","year":"2022","unstructured":"Kwon, S., Jung, W., Shim, K.: Cardinality estimation of approximate substring queries using deep learning. Proc. VLDB Endow. 15(11), 3145\u20133157 (2022)","journal-title":"Proc. VLDB Endow."},{"key":"975_CR36","doi-asserted-by":"crossref","unstructured":"Lao, J., Trummer, I.: Sqlbarber: A system leveraging large language models to generate customized and realistic sql workloads. (2025). arXiv preprint arXiv:2507.06192","DOI":"10.1145\/3722212.3725101"},{"issue":"11","key":"975_CR37","doi-asserted-by":"publisher","first-page":"2871","DOI":"10.14778\/3611479.3611494","volume":"16","author":"K Lee","year":"2023","unstructured":"Lee, K., Dutt, A., Narasayya, V., Chaudhuri, S.: Analyzing the impact of cardinality estimation on execution plans in microsoft sql server. Proc. VLDB Endow. 16(11), 2871\u20132883 (2023)","journal-title":"Proc. VLDB Endow."},{"issue":"3","key":"975_CR38","doi-asserted-by":"publisher","first-page":"204","DOI":"10.14778\/2850583.2850594","volume":"9","author":"V Leis","year":"2015","unstructured":"Leis, V., Gubichev, A., Mirchev, A., Boncz, P., Kemper, A., Neumann, T.: How good are query optimizers, really? Proc. VLDB Endow. 9(3), 204\u2013215 (2015)","journal-title":"Proc. VLDB Endow."},{"issue":"3","key":"975_CR39","doi-asserted-by":"publisher","first-page":"204","DOI":"10.14778\/2850583.2850594","volume":"9","author":"V Leis","year":"2015","unstructured":"Leis, V., Gubichev, A., Mirchev, A., Boncz, P., Kemper, A., Neumann, T.: How Good Are Query Optimizers, Really? Proc. VLDB Endow. 9(3), 204\u2013215 (2015)","journal-title":"Proc. VLDB Endow."},{"key":"975_CR40","unstructured":"Leis, V., Radke, B., Gubichev, A., Kemper, A., Neumann, T.: Cardinality estimation done right: Index-based join sampling. In Cidr, (2017)"},{"key":"975_CR41","doi-asserted-by":"crossref","unstructured":"Li, B., Lu, Y., Kandula, S.: Warper: Efficiently adapting learned cardinality estimators to data and workload drifts. In Proceedings of the 2022 International Conference on Management of Data, pp. 1920\u20131933 (2022)","DOI":"10.1145\/3514221.3526179"},{"issue":"3","key":"975_CR42","first-page":"1","volume":"2","author":"H Li","year":"2024","unstructured":"Li, H., Zhang, J., Liu, H., Fan, J., Zhang, X., Zhu, J., Wei, R., Pan, H., Li, C., Chen, H.: Codes: Towards building open-source language models for text-to-sql. Proc. ACM Manage. Data 2(3), 1\u201328 (2024)","journal-title":"Proc. ACM Manage. Data"},{"issue":"2","key":"975_CR43","doi-asserted-by":"publisher","first-page":"197","DOI":"10.14778\/3626292.3626302","volume":"17","author":"P Li","year":"2023","unstructured":"Li, P., Wei, W., Zhu, R., Ding, B., Zhou, J., Lu, H.: Alece: An attention-based learned cardinality estimator for spj queries on dynamic workloads. Proc. VLDB Endow. 17(2), 197\u2013210 (2023)","journal-title":"Proc. VLDB Endow."},{"key":"975_CR44","unstructured":"Li, Y., Li, H., Pu, Z., Zhang, J., Zhang, X., Ji, T., Sun, L., Li, C., Chen, H.: Is large language model good at database knob tuning? a comprehensive experimental evaluation. (2024). arXiv preprint arXiv:2408.02213"},{"key":"975_CR45","doi-asserted-by":"crossref","unstructured":"Li, Z., Yuan, H., Wang, H., Cong, G., Bing, L.: Llm-r2: A large language model enhanced rule-based rewrite system for boosting query efficiency. (2024). arXiv preprint arXiv:2404.12872","DOI":"10.14778\/3696435.3696440"},{"key":"975_CR46","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"11","key":"975_CR47","doi-asserted-by":"publisher","first-page":"1950","DOI":"10.14778\/3476249.3476254","volume":"14","author":"J Liu","year":"2021","unstructured":"Liu, J., Dong, W., Zhou, Q., Li, D.: Fauce: fast and accurate deep ensembles with uncertainty for cardinality estimation. Proc. VLDB Endow. 14(11), 1950\u20131963 (2021)","journal-title":"Proc. VLDB Endow."},{"key":"975_CR48","unstructured":"Liu, J., Mozafari, B.: Query rewriting via large language models. (2024). arXiv preprint arXiv:2403.09060"},{"key":"975_CR49","doi-asserted-by":"crossref","unstructured":"Lu, Y., Kandula, S., Knig, A. C., Chaudhuri, S.: Pre-training summarization models of structured datasets for cardinality estimation. Proc. VLDB Endow. (2021)","DOI":"10.14778\/3494124.3494127"},{"key":"975_CR50","doi-asserted-by":"crossref","unstructured":"Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., Alon, U., Dziri, N., Prabhumoye, S., Yang, Y., et al.: Self-refine: Iterative refinement with self-feedback. Adv. Neural. Inf. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-2019"},{"key":"975_CR51","doi-asserted-by":"crossref","unstructured":"Manakul, P., Liusie, A., Gales, M.: Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 9004\u20139017 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"975_CR52","doi-asserted-by":"crossref","unstructured":"Maynez, J., Narayan, S., Bohnet, B., McDonald, R.: On faithfulness and factuality in abstractive summarization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 1906\u20131919 (2020)","DOI":"10.18653\/v1\/2020.acl-main.173"},{"issue":"1","key":"975_CR53","doi-asserted-by":"publisher","first-page":"982","DOI":"10.14778\/1687627.1687738","volume":"2","author":"G Moerkotte","year":"2009","unstructured":"Moerkotte, G., Neumann, T., Steidl, G.: Preventing bad plans by bounding the impact of cardinality estimation errors. Proc. VLDB Endow. 2(1), 982\u2013993 (2009)","journal-title":"Proc. VLDB Endow."},{"key":"975_CR54","doi-asserted-by":"crossref","unstructured":"Mosbach, M., Pimentel, T., Ravfogel, S., Klakow, D., Elazar, Y.: Few-shot fine-tuning vs. in-context learning: A fair comparison and evaluation. In The 61st Annual Meeting Of The Association For Computational Linguistics, (2023)","DOI":"10.18653\/v1\/2023.findings-acl.779"},{"key":"975_CR55","unstructured":"Motl, J., Schulte, O.: The ctu prague relational learning repository. (2015). arXiv preprint arXiv:1511.03086"},{"key":"975_CR56","doi-asserted-by":"crossref","unstructured":"Moussa, R.: Tpc-h benchmark analytics scenarios and performances on hadoop data clouds. In Rachid Benlamri, editor, NDT (1), volume 293 of Communications in Computer and Information Science, pp. 220\u2013234. Springer, (2012)","DOI":"10.1007\/978-3-642-30507-8_20"},{"key":"975_CR57","unstructured":"Myntti, A., Henriksson, E., Laippala, V., Pyysalo, S.: Register always matters: Analysis of llm pretraining data through the lens of language variation. (2025). arXiv preprint arXiv:2504.01542"},{"issue":"11","key":"975_CR58","doi-asserted-by":"publisher","first-page":"2019","DOI":"10.14778\/3476249.3476259","volume":"14","author":"P Negi","year":"2021","unstructured":"Negi, P., Marcus, R., Kipf, A., Mao, H., Tatbul, N., Kraska, T., Alizadeh, M.: Flow-loss: learning cardinality estimates that matter. Proc. VLDB Endow. 14(11), 2019\u20132032 (2021)","journal-title":"Proc. VLDB Endow."},{"issue":"6","key":"975_CR59","doi-asserted-by":"publisher","first-page":"1520","DOI":"10.14778\/3583140.3583164","volume":"16","author":"P Negi","year":"2023","unstructured":"Negi, P., Wu, Z., Kipf, A., Tatbul, N., Marcus, R., Madden, S., Kraska, T., Alizadeh, M.: Robust query driven cardinality estimation under changing workloads. Proc. VLDB Endow. 16(6), 1520\u20131533 (2023)","journal-title":"Proc. VLDB Endow."},{"key":"975_CR60","unstructured":"OpenAI. Gpt-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/, (2023)"},{"key":"975_CR61","doi-asserted-by":"crossref","unstructured":"O\u2019Neil, P., O\u2019Neil, E., Chen, X., Revilak, S.: The star schema benchmark and augmented fact table indexing. In Performance Evaluation and Benchmarking: First TPC Technology Conference, TPCTC 2009, Lyon, France, August 24-28, 2009, Revised Selected Papers 1, pp. 237\u2013252. Springer, (2009)","DOI":"10.1007\/978-3-642-10424-4_17"},{"key":"975_CR62","doi-asserted-by":"crossref","unstructured":"Pan, L., Saxon, M., Xu, W., Nathani, D., Wang, X., Wang, W. Y.: Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies. (2023). arXiv preprint arXiv:2308.03188","DOI":"10.1162\/tacl_a_00660"},{"key":"975_CR63","doi-asserted-by":"crossref","unstructured":"Park, Y., Zhong, S., Mozafari, B.: Quicksel: Quick selectivity learning with mixture models. In Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, pp. 1017\u20131033 (2020)","DOI":"10.1145\/3318464.3389727"},{"key":"975_CR64","unstructured":"Poosala, V., Ioannidis, Y.E.: Selectivity estimation without the attribute value independence assumption. In VLDB 97, 486\u2013495 (1997)"},{"key":"975_CR65","unstructured":"PostgreSQL Documentation. Row Estimation Examples, 2020. (2020)"},{"key":"975_CR66","doi-asserted-by":"crossref","unstructured":"Rawte, V., Chakraborty, S., Pathak, A., Sarkar, A., Tonmoy, S.M. T. I., Chadha, A., Sheth, A., Das, A.: The troubling emergence of hallucination in large language models-an extensive definition, quantification, and prescriptive remediations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 2541\u20132573 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.155"},{"key":"975_CR67","unstructured":"Schulman, J.: Reinforcement learning from human feedback: Progress and challenges. In Berkeley EECS Colloquium. YouTube www.youtube.com\/watch, (2023)"},{"key":"975_CR68","volume-title":"The Evidential Foundations of Probabilistic Reasoning","author":"DA Schum","year":"2001","unstructured":"Schum, D.A.: The Evidential Foundations of Probabilistic Reasoning. Northwestern University Press (2001)"},{"key":"975_CR69","doi-asserted-by":"crossref","unstructured":"Selinger, P. G., Astrahan, M. M., Chamberlin, D. D., Lorie, R. A., Price, T. G.: Access path selection in a relational database management system. In Proceedings of the 1979 ACM SIGMOD international conference on Management of data, pp. 23\u201334 (1979)","DOI":"10.1145\/582095.582099"},{"key":"975_CR70","doi-asserted-by":"crossref","unstructured":"Shetiya, S., Thirumuruganathan, S., Koudas, N., Das, G.: Astrid: accurate selectivity estimation for string predicates using deep learning. Proc. VLDB Endow. 14(4), (2020)","DOI":"10.14778\/3436905.3436907"},{"key":"975_CR71","doi-asserted-by":"crossref","unstructured":"Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., Yao, S.: Reflexion: Language agents with verbal reinforcement learning. Adv. Neural Inf. Process. Syst. 36, (2024)","DOI":"10.52202\/075280-0377"},{"key":"975_CR72","unstructured":"Singh, V., Vaidya, K. E., Kumar, V. B., Khosla, S., Narayanaswamy, M., Gangadharaiah, R., Kraska, T.: Panda: Performance debugging for databases using llm agents. (2024)"},{"issue":"12","key":"975_CR73","doi-asserted-by":"publisher","first-page":"3770","DOI":"10.14778\/3554821.3554896","volume":"15","author":"I Trummer","year":"2022","unstructured":"Trummer, I.: From bert to gpt-3 codex: harnessing the potential of very large language models for data management. Proc. VLDB Endow. 15(12), 3770\u20133773 (2022)","journal-title":"Proc. VLDB Endow."},{"issue":"9","key":"975_CR74","doi-asserted-by":"publisher","first-page":"1640","DOI":"10.14778\/3461535.3461552","volume":"14","author":"X Wang","year":"2021","unstructured":"Wang, X., Qu, C., Wu, W., Wang, J., Zhou, Q.: Are we ready for learned cardinality estimation? Proc. VLDB Endow. 14(9), 1640\u20131654 (2021)","journal-title":"Proc. VLDB Endow."},{"key":"975_CR75","unstructured":"Wehrstein, J., Binnig, C., \u00d6zcan, F., Vasudevan, S., Gan, Y., Wang,Y.: Towards foundation database models"},{"key":"975_CR76","unstructured":"Wettig, A., Gupta, A., Malik, S., Chen, D.: Qurating: Selecting high-quality data for training language models. In International Conference on Machine Learning, pp. 52915\u201352971. PMLR, (2024)"},{"key":"975_CR77","doi-asserted-by":"crossref","unstructured":"Woltmann, L., Hartmann, C., Thiele, M., Habich, D., Lehner,W.: Cardinality estimation with local deep learning models. In Proceedings of the second international workshop on exploiting artificial intelligence techniques for data management, pp. 1\u20138, (2019)","DOI":"10.1145\/3329859.3329875"},{"issue":"1","key":"975_CR78","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3639293","volume":"2","author":"P Wu","year":"2024","unstructured":"Wu, P., Ives, Z.G.: Modeling shifting workloads for learned database systems. Proc. ACM Manage. Data 2(1), 1\u201327 (2024)","journal-title":"Proc. ACM Manage. Data"},{"issue":"2","key":"975_CR79","doi-asserted-by":"publisher","first-page":"272","DOI":"10.14778\/3489496.3489508","volume":"15","author":"R Wu","year":"2021","unstructured":"Wu, R., Ding, B., Chu, X., Wei, Z., Dai, X., Guan, T., Zhou, J.: Learning to be a statistician: learned estimator for number of distinct values. Proc. VLDB Endow. 15(2), 272\u2013284 (2021)","journal-title":"Proc. VLDB Endow."},{"issue":"1","key":"975_CR80","first-page":"1","volume":"1","author":"Z Wu","year":"2023","unstructured":"Wu, Z., Negi, P., Alizadeh, M., Kraska, T., Madden, S.: Factorjoin: a new cardinality estimation framework for join queries. Proc. ACM Manage. Data 1(1), 1\u201327 (2023)","journal-title":"Proc. ACM Manage. Data"},{"key":"975_CR81","unstructured":"Wu, Z., Shaikhha, A., Zhu, R., Zeng, K., Han, Y., Zhou, J.: Bayescard: Revitilizing bayesian frameworks for cardinality estimation. (2020). arXiv preprint"},{"key":"975_CR82","doi-asserted-by":"crossref","unstructured":"Xu, C., Xu, Y., Wang, S., Liu, Y., Zhu, C., McAuley, J.: Small models are valuable plug-ins for large language models. (2023). arXiv preprint arXiv:2305.08848","DOI":"10.18653\/v1\/2024.findings-acl.18"},{"key":"975_CR83","unstructured":"Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., Lv, C., et al. Qwen3 technical report. (2025). arXiv preprint arXiv:2505.09388"},{"issue":"1","key":"975_CR84","doi-asserted-by":"publisher","first-page":"61","DOI":"10.14778\/3421424.3421432","volume":"14","author":"Z Yang","year":"2020","unstructured":"Yang, Z., Kamsetty, A., Luan, S., Liang, E., Duan, Y., Chen, X., Stoica, I.: Neurocard: one cardinality estimator for all tables. Proc. VLDB Endow. 14(1), 61\u201373 (2020)","journal-title":"Proc. VLDB Endow."},{"key":"975_CR85","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liang, E., Kamsetty, A., Wu, C., Duan, Y., Chen, X., Abbeel, P., Hellerstein, J. M., Krishnan, S., Stoica, I.: Deep unsupervised cardinality estimation. Proc. VLDB Endow. 13(3)","DOI":"10.14778\/3368289.3368294"},{"key":"975_CR86","doi-asserted-by":"crossref","unstructured":"Zeng, T., Lan, J., Ma, J., Wei, W., Zhu, R., Li, P., Ding, B., Lian, D., Wei, Z., Zhou, J.: Price: A pretrained model for cross-database cardinality estimation. (2024). arXiv preprint arXiv:2406.01027","DOI":"10.14778\/3712221.3712231"},{"key":"975_CR87","unstructured":"Zhang, J., Qiao, D., Yang, M., Wei, Q.: Regurgitative training: The value of real data in training large language models. Available at SSRN 4870843, (2024)"},{"key":"975_CR88","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhang, R., Zhang, J., Ye, Y., Luo, Z., Feng, Z., Ma, Y.: Llamafactory: Unified efficient fine-tuning of 100+ language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), Bangkok, Thailand, (2024). Association for Computational Linguistics","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"975_CR89","unstructured":"Zhou, X., Li, G., Liu, Z.: Llm as dba. (2023). arXiv preprint arXiv:2308.05481"},{"issue":"10","key":"975_CR90","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.14778\/3675034.3675043","volume":"17","author":"X Zhou","year":"2024","unstructured":"Zhou, X., Li, G., Sun, Z., Liu, Z., Chen, W., Wu, J., Liu, J., Feng, R., Zeng, G.: D-bot: Database diagnosis system using large language models. Proc. VLDB Endow. 17(10), 2514\u20132527 (2024)","journal-title":"Proc. VLDB Endow."},{"issue":"1","key":"975_CR91","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/s41019-023-00235-6","volume":"9","author":"X Zhou","year":"2024","unstructured":"Zhou, X., Sun, Z., Li, G.: Db-gpt: Large language model meets database. Data Sci. Eng. 9(1), 102\u2013111 (2024)","journal-title":"Data Sci. Eng."},{"issue":"5","key":"975_CR92","doi-asserted-by":"publisher","first-page":"980","DOI":"10.14778\/3641204.3641209","volume":"17","author":"R Zhu","year":"2024","unstructured":"Zhu, R., Weng, L., Wei, W., Wu, D., Peng, J., Wang, Y., Ding, B., Lian, D., Zheng, B., Zhou, J.: Pilotscope: Steering databases with machine learning drivers. Proc. VLDB Endow. 17(5), 980\u2013993 (2024)","journal-title":"Proc. VLDB Endow."}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-026-00975-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00778-026-00975-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-026-00975-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:14:18Z","timestamp":1790230458000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00778-026-00975-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,24]]},"references-count":92,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["975"],"URL":"https:\/\/doi.org\/10.1007\/s00778-026-00975-7","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,24]]},"assertion":[{"value":"19 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"43"}}