@inproceedings{lu-etal-2026-dsr,
title = "{DSR}-{SQL}: Dual-Schema Reasoning for Text-to-{SQL} and {PI}-{MCE} Optimized Schema Linking",
author = "Lu, Hu and
Li, Fanghao and
Han, Dongqi and
Zhang, Yao",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1688/",
pages = "38396--38410",
ISBN = "979-8-89176-459-0",
abstract = "Small open-source LLMs for Text-to-SQL face a trade-off between schema completeness and input noise. Pruned schemas provide compact contexts for SQL generation but are vulnerable to schema-linking errors, while full schemas preserve complete database information but may introduce substantial irrelevant context. We propose DSR-SQL, a dual-schema reasoning framework that generates SQL candidates from both pruned and full schemas. The pruned-schema path supports focused reasoning, whereas the full-schema path helps recover schema elements that may be missed during pruning. The generated candidates are refined with execution feedback and integrated through an execution-aware merger or a deterministic fallback selector. To improve the reliability of the pruned-schema path, we further introduce a Permutation-Invariant Minimum Cross-Entropy (PI-MCE) loss for table selection, which reduces the sequence-order bias caused by autoregressive training on unordered table sets. Experiments on the BIRD benchmark show that DSR-SQL achieves 67.41{\%} execution accuracy on the test set using a 7B-parameter model. These results demonstrate the effectiveness of dual-schema reasoning, with PI-MCE providing complementary improvements in table selection for smaller open-source LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2026-dsr">
<titleInfo>
<title>DSR-SQL: Dual-Schema Reasoning for Text-to-SQL and PI-MCE Optimized Schema Linking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hu</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fanghao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongqi</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Small open-source LLMs for Text-to-SQL face a trade-off between schema completeness and input noise. Pruned schemas provide compact contexts for SQL generation but are vulnerable to schema-linking errors, while full schemas preserve complete database information but may introduce substantial irrelevant context. We propose DSR-SQL, a dual-schema reasoning framework that generates SQL candidates from both pruned and full schemas. The pruned-schema path supports focused reasoning, whereas the full-schema path helps recover schema elements that may be missed during pruning. The generated candidates are refined with execution feedback and integrated through an execution-aware merger or a deterministic fallback selector. To improve the reliability of the pruned-schema path, we further introduce a Permutation-Invariant Minimum Cross-Entropy (PI-MCE) loss for table selection, which reduces the sequence-order bias caused by autoregressive training on unordered table sets. Experiments on the BIRD benchmark show that DSR-SQL achieves 67.41% execution accuracy on the test set using a 7B-parameter model. These results demonstrate the effectiveness of dual-schema reasoning, with PI-MCE providing complementary improvements in table selection for smaller open-source LLMs.</abstract>
<identifier type="citekey">lu-etal-2026-dsr</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1688/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>38396</start>
<end>38410</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DSR-SQL: Dual-Schema Reasoning for Text-to-SQL and PI-MCE Optimized Schema Linking
%A Lu, Hu
%A Li, Fanghao
%A Han, Dongqi
%A Zhang, Yao
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F lu-etal-2026-dsr
%X Small open-source LLMs for Text-to-SQL face a trade-off between schema completeness and input noise. Pruned schemas provide compact contexts for SQL generation but are vulnerable to schema-linking errors, while full schemas preserve complete database information but may introduce substantial irrelevant context. We propose DSR-SQL, a dual-schema reasoning framework that generates SQL candidates from both pruned and full schemas. The pruned-schema path supports focused reasoning, whereas the full-schema path helps recover schema elements that may be missed during pruning. The generated candidates are refined with execution feedback and integrated through an execution-aware merger or a deterministic fallback selector. To improve the reliability of the pruned-schema path, we further introduce a Permutation-Invariant Minimum Cross-Entropy (PI-MCE) loss for table selection, which reduces the sequence-order bias caused by autoregressive training on unordered table sets. Experiments on the BIRD benchmark show that DSR-SQL achieves 67.41% execution accuracy on the test set using a 7B-parameter model. These results demonstrate the effectiveness of dual-schema reasoning, with PI-MCE providing complementary improvements in table selection for smaller open-source LLMs.
%U https://aclanthology.org/2026.emnlp-main.1688/
%P 38396-38410
Markdown (Informal)
[DSR-SQL: Dual-Schema Reasoning for Text-to-SQL and PI-MCE Optimized Schema Linking](https://aclanthology.org/2026.emnlp-main.1688/) (Lu et al., EMNLP 2026)
ACL