Knowledge Distillation for Low-Resource Open-source Text-to-SQL Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiu, Tianhao, Chen, Xiaojun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910247347552256
author Qiu, Tianhao
Chen, Xiaojun
author_facet Qiu, Tianhao
Chen, Xiaojun
contents Text-to-SQL converts natural language questions into executable SQL queries, enabling non-technical users to access relational databases for analytics and intelligent data services. In real-world scenarios, performance is often constrained by low-resource settings, where high-quality annotated \texttt{<question, SQL>} pairs are scarce, particularly for domain-specific databases. Additional challenges include opaque schema definitions, abbreviations, and implicit business logic that are not explicitly encoded in the schema. Existing data synthesis and prompting techniques improve coverage but often fail to produce task-specific, semantically grounded examples aligned with database constraints. To address these challenges, we propose a knowledge-aware Text-to-SQL framework that constructs task-specific knowledge base including schema semantics, abbreviations, business logic, and query patterns, and injects them into both training and inference. This framework generates diverse, contextually grounded synthetic training data and enhances inference through targeted knowledge retrieval. Experiments on seven benchmarks, covering both general and domain-specific datasets, demonstrate that our approach substantially improves the performance of open-source and closed-source large language models in Text-to-SQL tasks, especially in low-resource domain-specific settings, enhancing generalization, robustness, and adaptability.
format Preprint
id arxiv_https___arxiv_org_abs_2605_22843
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Knowledge Distillation for Low-Resource Open-source Text-to-SQL Model
Qiu, Tianhao
Chen, Xiaojun
Computation and Language
Information Retrieval
68T50, 68P15
H.2.3; I.2.7; I.2.6
Text-to-SQL converts natural language questions into executable SQL queries, enabling non-technical users to access relational databases for analytics and intelligent data services. In real-world scenarios, performance is often constrained by low-resource settings, where high-quality annotated \texttt{<question, SQL>} pairs are scarce, particularly for domain-specific databases. Additional challenges include opaque schema definitions, abbreviations, and implicit business logic that are not explicitly encoded in the schema. Existing data synthesis and prompting techniques improve coverage but often fail to produce task-specific, semantically grounded examples aligned with database constraints. To address these challenges, we propose a knowledge-aware Text-to-SQL framework that constructs task-specific knowledge base including schema semantics, abbreviations, business logic, and query patterns, and injects them into both training and inference. This framework generates diverse, contextually grounded synthetic training data and enhances inference through targeted knowledge retrieval. Experiments on seven benchmarks, covering both general and domain-specific datasets, demonstrate that our approach substantially improves the performance of open-source and closed-source large language models in Text-to-SQL tasks, especially in low-resource domain-specific settings, enhancing generalization, robustness, and adaptability.
title Knowledge Distillation for Low-Resource Open-source Text-to-SQL Model
topic Computation and Language
Information Retrieval
68T50, 68P15
H.2.3; I.2.7; I.2.6
url https://arxiv.org/abs/2605.22843