Are LLMs Overkill for Databases?: A Study on the Finiteness of SQL

• URL: http://arxiv.org/abs/2603.25568v1
• Date: Thu, 26 Mar 2026 15:40:36 GMT
• Title: Are LLMs Overkill for Databases?: A Study on the Finiteness of SQL
• Abstract summary: We show that translations of natural language questions are finite in practical complexity.<n>There is no clear monotonic relationship between increases in database table count and increases in complexity.<n>This suggests that while LLMs for code generation can be useful, in the domain of database access, they may be operating in a narrow, highly formulaic space.
• Score: 7.475038197264023
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Translating natural language to SQL for data retrieval has become more accessible thanks to code generation LLMs. But how hard is it to generate SQL code? While databases can become unbounded in complexity, the complexity of queries is bounded by real life utility and human needs. With a sample of 376 databases, we show that SQL queries, as translations of natural language questions are finite in practical complexity. There is no clear monotonic relationship between increases in database table count and increases in complexity of SQL queries. In their template forms, SQL queries follow a Power Law-like distribution of frequency where 70% of our tested queries can be covered with just 13% of all template types, indicating that the high majority of SQL queries are predictable. This suggests that while LLMs for code generation can be useful, in the domain of database access, they may be operating in a narrow, highly formulaic space where templates could be safer, cheaper, and auditable.

Related papers

• Weaver: Interweaving SQL and LLM for Table Reasoning [62.55797244714265]
  Weaver generates a flexible, step-by-step plan that combinessql for structured data retrieval with LLMs for semantic processing.<n>Weaver consistently outperforms state-of-the-art methods across four TableQA datasets.
  arXiv  Detail & Related papers  (2025-05-25T03:27:37Z)
• Can the Rookies Cut the Tough Cookie? Exploring the Use of LLMs for SQL Equivalence Checking [15.42143912008553]
  We introduce a novel, realistic, and sufficiently complex benchmark called SQLEquiQuest for query equivalence checking.<n>We evaluate several state-of-the-art LLMs using various prompting strategies and carefully constructed in-context learning examples.<n>Our analysis shows that LLMs exhibit a strong bias for equivalence predictions, with consistently poor performance over non-equivalent pairs.
  arXiv  Detail & Related papers  (2024-12-07T06:50:12Z)
• PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL [54.304872649870575]
  Large Language Models (LLMs) have emerged as powerful tools for Text-to-sense tasks. In this study, we propose that employing query group partitioning allows LLMs to focus on learning the thought processes specific to a single problem type.
  arXiv  Detail & Related papers  (2024-09-21T09:33:14Z)
• Relational Database Augmented Large Language Model [59.38841050766026]
  Large language models (LLMs) excel in many natural language processing (NLP) tasks. They can only incorporate new knowledge through training or supervised fine-tuning processes. This precise, up-to-date, and private information is typically stored in relational databases.
  arXiv  Detail & Related papers  (2024-07-21T06:19:10Z)
• Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databases [2.933060994339853]
  We investigate the potential of an alternative query language with simpler syntax and modular specification of complex queries. The proposed alternative query language is called Query Plan Language (QPL) We present ways to address the challenge of complex queries in an iterative, user-controlled manner.
  arXiv  Detail & Related papers  (2023-12-22T16:16:15Z)
• LLM-SQL-Solver: Can LLMs Determine SQL Equivalence? [7.59813709836711]
  Large Language Models (LLMs) have shown strong reasoning capability in conversation, question answering and solving challenges.<n>To assist LLMs in generating high quality responses, we present two prompting techniques: Miniature & Mull and Explain & Compare.
  arXiv  Detail & Related papers  (2023-12-16T05:01:23Z)
• UNITE: A Unified Benchmark for Text-to-SQL Evaluation [72.72040379293718]
  We introduce a UNIfied benchmark for Text-to-domain systems. It is composed of publicly available text-to-domain datasets and 29K databases. Compared to the widely used Spider benchmark, we introduce a threefold increase in SQL patterns.
  arXiv  Detail & Related papers  (2023-05-25T17:19:52Z)
• Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs [89.68522473384522]
  We present Bird, a big benchmark for large-scale database grounded in text-to-efficient tasks. Our emphasis on database values highlights the new challenges of dirty database contents. Even the most effective text-to-efficient models, i.e. ChatGPT, achieves only 40.08% in execution accuracy.
  arXiv  Detail & Related papers  (2023-05-04T19:02:29Z)
• Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering [78.9863753810787]
  A large amount of world's knowledge is stored in structured databases. query languages can answer questions that require complex reasoning, as well as offering full explainability.
  arXiv  Detail & Related papers  (2021-08-05T22:04:13Z)
• Translating synthetic natural language to database queries: a polyglot deep learning framework [0.0]
  Polyglotter supports the mapping of natural language searches to database queries. It does not require the creation of manually annotated data for training. Our results indicate that our framework performs well on both synthetic and real databases.
  arXiv  Detail & Related papers  (2021-04-14T17:43:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.