CodexDB: synthesizing code for query processing from natural language instructions using GPT-3 codex
Abstract
CodexDB enables users to customize SQL query processing via natural language instructions. CodexDB is based on OpenAI's GPT-3 Codex model which translates text into code. It is a framework on top of GPT-3 Codex that decomposes complex SQL queries into a series of simple processing steps, described in natural language. Processing steps are enriched with user-provided instructions and descriptions of database properties. Codex translates the resulting text into query processing code. An early prototype of CodexDB is able to generate correct code for up to 81% of queries for the WikiSQL benchmark and for up to 62% on the SPIDER benchmark.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Large language models (LLMs) have emerged as a new paradigm for Text-to-SQL task.
“Large language models (LLMs) have emerged as a new paradigm for Text-to-SQL task.”
From Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation (2024) · cites this paper as [50]
Cites
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741 · see citing works
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
Gao, D., Wang, H., Li, Y., Sun, X., Qian, Y., Ding, B., & Zhou, J. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3641204.3641221 · Cited by 342 · see citing works
Incorporating Generative AI into Software Development Education
Petrovska, O., Clift, L., Moller, F., & Pearsall, R. (2024) · Proceedings of the 8th Conference on Computing Education Practice · doi:10.1145/3633053.3633057 · Cited by 75 · see citing works
MeshAgent: enabling reliable network management with large language models
Zhou, Y., Hsieh, K., Mani, S. K., Kandula, S., & Liu, Z. (2025) · Proceedings of the ACM on Measurement and Analysis of Computing Systems · doi:10.1145/3771567 · Cited by 7 · see citing works
- Authors
- Trummer, I.
- Affiliations
- Cornell University (US)
- Corresponding author
- Trummer, Immanuel
- ORCID
- Trummer, Immanuel
- Venue
- Proceedings of the VLDB Endowment
- Published
- 2022-07
- Volume
- 15
- Issue
- 11
- Pages
- 2921-2928
- ISSN
- 2150-8097 (ISSN-L)
- OpenAlex
- W4312537169
- Cited by
- 65
- References
- 2
- Citations by year
- 2026: 8 · 2025: 20 · 2024: 15 · 2023: 21 · 2022: 1
- FWCI
- 6.32
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Proceedings of the VLDB Endowment (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Advanced Database Systems and Queries
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- natural language to SQL translation, SQL query processing, large language models, query decomposition, database education, WikiSQL, Spider benchmark, code generation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
