@inproceedings{hao-etal-2025-genlink,
title = "{G}en{L}ink: Generation-Driven Schema-Linking via Multi-Model Learning for Text-to-{SQL}",
author = "Hao, Zhifeng and
Huang, Junqi and
Shi, Shaobin and
Cai, Ruichu and
Xu, Boyan",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1518/",
pages = "29880--29893",
ISBN = "979-8-89176-332-6",
abstract = "Schema linking is widely recognized as a key factor in improving text-to-SQL performance. Supervised fine-tuning approaches enhance SQL generation quality by explicitly fine-tuning schema linking as an extraction task. However, they suffer from two major limitations: (i) The training corpus of small language models restricts their cross-domain generalization ability. (ii) The extraction-based fine-tuning process struggles to capture complex linking patterns. To address these issues, we propose \textbf{GenLink}, a generation-driven schema-linking framework based on multi-model learning. Instead of explicitly extracting schema elements, GenLink enhances linking through a generation-based learning process, effectively capturing implicit schema relationships. By integrating multiple small language models, GenLink improves schema-linking recall rate and ensures robust cross-domain adaptability. Experimental results on the BIRD and Spider benchmarks validate the effectiveness of GenLink, achieving execution accuracies of 67.34{\%} (BIRD), 89.7{\%} (Spider development set), and 87.8{\%} (Spider test set), demonstrating its superiority in handling diverse and complex database schemas."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hao-etal-2025-genlink">
<titleInfo>
<title>GenLink: Generation-Driven Schema-Linking via Multi-Model Learning for Text-to-SQL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhifeng</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junqi</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaobin</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruichu</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boyan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Schema linking is widely recognized as a key factor in improving text-to-SQL performance. Supervised fine-tuning approaches enhance SQL generation quality by explicitly fine-tuning schema linking as an extraction task. However, they suffer from two major limitations: (i) The training corpus of small language models restricts their cross-domain generalization ability. (ii) The extraction-based fine-tuning process struggles to capture complex linking patterns. To address these issues, we propose GenLink, a generation-driven schema-linking framework based on multi-model learning. Instead of explicitly extracting schema elements, GenLink enhances linking through a generation-based learning process, effectively capturing implicit schema relationships. By integrating multiple small language models, GenLink improves schema-linking recall rate and ensures robust cross-domain adaptability. Experimental results on the BIRD and Spider benchmarks validate the effectiveness of GenLink, achieving execution accuracies of 67.34% (BIRD), 89.7% (Spider development set), and 87.8% (Spider test set), demonstrating its superiority in handling diverse and complex database schemas.</abstract>
<identifier type="citekey">hao-etal-2025-genlink</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1518/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>29880</start>
<end>29893</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GenLink: Generation-Driven Schema-Linking via Multi-Model Learning for Text-to-SQL
%A Hao, Zhifeng
%A Huang, Junqi
%A Shi, Shaobin
%A Cai, Ruichu
%A Xu, Boyan
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F hao-etal-2025-genlink
%X Schema linking is widely recognized as a key factor in improving text-to-SQL performance. Supervised fine-tuning approaches enhance SQL generation quality by explicitly fine-tuning schema linking as an extraction task. However, they suffer from two major limitations: (i) The training corpus of small language models restricts their cross-domain generalization ability. (ii) The extraction-based fine-tuning process struggles to capture complex linking patterns. To address these issues, we propose GenLink, a generation-driven schema-linking framework based on multi-model learning. Instead of explicitly extracting schema elements, GenLink enhances linking through a generation-based learning process, effectively capturing implicit schema relationships. By integrating multiple small language models, GenLink improves schema-linking recall rate and ensures robust cross-domain adaptability. Experimental results on the BIRD and Spider benchmarks validate the effectiveness of GenLink, achieving execution accuracies of 67.34% (BIRD), 89.7% (Spider development set), and 87.8% (Spider test set), demonstrating its superiority in handling diverse and complex database schemas.
%U https://aclanthology.org/2025.emnlp-main.1518/
%P 29880-29893
Markdown (Informal)
[GenLink: Generation-Driven Schema-Linking via Multi-Model Learning for Text-to-SQL](https://aclanthology.org/2025.emnlp-main.1518/) (Hao et al., EMNLP 2025)
ACL