@inproceedings{nguyen-etal-2025-sqlong,
title = "{SQL}ong: Enhanced {NL}2{SQL} for Longer Contexts with {LLM}s",
author = "Nguyen, Dai Quoc and
Hoang, Cong Duy Vu and
Vu, Duy Quang and
Tangari, Gioacchino and
Vu, Thanh and
Dharmasiri, Don and
Li, Yuan-Fang and
Duong, Long",
editor = "Chang, Shuaichen and
Hulsebos, Madelon and
Liu, Qian and
Chen, Wenhu and
Sun, Huan",
booktitle = "Proceedings of the 4th Table Representation Learning Workshop",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.trl-1.5/",
doi = "10.18653/v1/2025.trl-1.5",
pages = "47--55",
ISBN = "979-8-89176-268-8",
abstract = "Open-weight large language models (LLMs) have significantly advanced performance in the Natural Language to SQL (NL2SQL) task. However, their effectiveness diminishes when dealing with large database schemas, as the context length increases. To address this limitation, we present SQLong, a novel and efficient data augmentation framework designed to enhance LLM performance in long-context scenarios for the NL2SQL task. SQLong generates augmented datasets by extending existing database schemas with additional synthetic CREATE TABLE commands and corresponding data rows, sampled from diverse schemas in the training data. This approach effectively simulates long-context scenarios during finetuning and evaluation. Through experiments on the Spider and BIRD datasets, we demonstrate that LLMs finetuned with SQLong-augmented data significantly outperform those trained on standard datasets. These imply SQLong{'}s practical implementation and its impact on improving NL2SQL capabilities in real-world settings with complex database schemas."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2025-sqlong">
<titleInfo>
<title>SQLong: Enhanced NL2SQL for Longer Contexts with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dai</namePart>
<namePart type="given">Quoc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cong</namePart>
<namePart type="given">Duy</namePart>
<namePart type="given">Vu</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duy</namePart>
<namePart type="given">Quang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gioacchino</namePart>
<namePart type="family">Tangari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Don</namePart>
<namePart type="family">Dharmasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan-Fang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Duong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Table Representation Learning Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuaichen</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madelon</namePart>
<namePart type="family">Hulsebos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-268-8</identifier>
</relatedItem>
<abstract>Open-weight large language models (LLMs) have significantly advanced performance in the Natural Language to SQL (NL2SQL) task. However, their effectiveness diminishes when dealing with large database schemas, as the context length increases. To address this limitation, we present SQLong, a novel and efficient data augmentation framework designed to enhance LLM performance in long-context scenarios for the NL2SQL task. SQLong generates augmented datasets by extending existing database schemas with additional synthetic CREATE TABLE commands and corresponding data rows, sampled from diverse schemas in the training data. This approach effectively simulates long-context scenarios during finetuning and evaluation. Through experiments on the Spider and BIRD datasets, we demonstrate that LLMs finetuned with SQLong-augmented data significantly outperform those trained on standard datasets. These imply SQLong’s practical implementation and its impact on improving NL2SQL capabilities in real-world settings with complex database schemas.</abstract>
<identifier type="citekey">nguyen-etal-2025-sqlong</identifier>
<identifier type="doi">10.18653/v1/2025.trl-1.5</identifier>
<location>
<url>https://aclanthology.org/2025.trl-1.5/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>47</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SQLong: Enhanced NL2SQL for Longer Contexts with LLMs
%A Nguyen, Dai Quoc
%A Hoang, Cong Duy Vu
%A Vu, Duy Quang
%A Tangari, Gioacchino
%A Vu, Thanh
%A Dharmasiri, Don
%A Li, Yuan-Fang
%A Duong, Long
%Y Chang, Shuaichen
%Y Hulsebos, Madelon
%Y Liu, Qian
%Y Chen, Wenhu
%Y Sun, Huan
%S Proceedings of the 4th Table Representation Learning Workshop
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-268-8
%F nguyen-etal-2025-sqlong
%X Open-weight large language models (LLMs) have significantly advanced performance in the Natural Language to SQL (NL2SQL) task. However, their effectiveness diminishes when dealing with large database schemas, as the context length increases. To address this limitation, we present SQLong, a novel and efficient data augmentation framework designed to enhance LLM performance in long-context scenarios for the NL2SQL task. SQLong generates augmented datasets by extending existing database schemas with additional synthetic CREATE TABLE commands and corresponding data rows, sampled from diverse schemas in the training data. This approach effectively simulates long-context scenarios during finetuning and evaluation. Through experiments on the Spider and BIRD datasets, we demonstrate that LLMs finetuned with SQLong-augmented data significantly outperform those trained on standard datasets. These imply SQLong’s practical implementation and its impact on improving NL2SQL capabilities in real-world settings with complex database schemas.
%R 10.18653/v1/2025.trl-1.5
%U https://aclanthology.org/2025.trl-1.5/
%U https://doi.org/10.18653/v1/2025.trl-1.5
%P 47-55
Markdown (Informal)
[SQLong: Enhanced NL2SQL for Longer Contexts with LLMs](https://aclanthology.org/2025.trl-1.5/) (Nguyen et al., TRL 2025)
ACL
- Dai Quoc Nguyen, Cong Duy Vu Hoang, Duy Quang Vu, Gioacchino Tangari, Thanh Vu, Don Dharmasiri, Yuan-Fang Li, and Long Duong. 2025. SQLong: Enhanced NL2SQL for Longer Contexts with LLMs. In Proceedings of the 4th Table Representation Learning Workshop, pages 47–55, Vienna, Austria. Association for Computational Linguistics.