@inproceedings{zhang-etal-2026-cores,
title = "{CORES}: Code-Oriented Reasoning for Complex Text-to-{SQL} and Generalizable {T}able{QA}",
author = "Zhang, Meng and
Jin, Ruochun and
Peng, Yuanxi and
Yang, Wenjing and
Wang, Haotian and
Sun, Liting and
Hu, Kun and
Yang, Silin and
Ke-di, Zhang",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.237/",
pages = "4827--4847",
ISBN = "979-8-89176-395-1",
abstract = "Text-to-SQL aims to bridge the gap between human intent and relational databases. While LLMs have shown proficiency in generating simple SQL queries, they struggle with complex analytical tasks. Moreover, models fine-tuned on SQL generation often suffer from catastrophic forgetting, which lose the versatility of procedural reasoning and pertaining to generation constraints. Inspired by the usage of high-resource programming languages as LLM reasoning intermediaries, we propose CORES model, which leverages Python as a procedural reasoning pivot to enhance both complex SQL generation and tabular reasoning. It decomposes complex queries into Python reasoning traces before generating the final SQL, which bridges the gap between procedural reasoning and declarative expression. In order to internalize this reasoning capability, we fine-tune LLMs via GRPO with tailored process reward functions that mitigate the sparse feedback problem. We experimentally verify the effectiveness of CORES on six text-to-SQL benchmarks, where ours outperforms baselines by 6.44{\%} on average, while maintains good capability on three tableQA benchmarks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-cores">
<titleInfo>
<title>CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruochun</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanxi</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haotian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liting</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Ke-di</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Text-to-SQL aims to bridge the gap between human intent and relational databases. While LLMs have shown proficiency in generating simple SQL queries, they struggle with complex analytical tasks. Moreover, models fine-tuned on SQL generation often suffer from catastrophic forgetting, which lose the versatility of procedural reasoning and pertaining to generation constraints. Inspired by the usage of high-resource programming languages as LLM reasoning intermediaries, we propose CORES model, which leverages Python as a procedural reasoning pivot to enhance both complex SQL generation and tabular reasoning. It decomposes complex queries into Python reasoning traces before generating the final SQL, which bridges the gap between procedural reasoning and declarative expression. In order to internalize this reasoning capability, we fine-tune LLMs via GRPO with tailored process reward functions that mitigate the sparse feedback problem. We experimentally verify the effectiveness of CORES on six text-to-SQL benchmarks, where ours outperforms baselines by 6.44% on average, while maintains good capability on three tableQA benchmarks.</abstract>
<identifier type="citekey">zhang-etal-2026-cores</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.237/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>4827</start>
<end>4847</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA
%A Zhang, Meng
%A Jin, Ruochun
%A Peng, Yuanxi
%A Yang, Wenjing
%A Wang, Haotian
%A Sun, Liting
%A Hu, Kun
%A Yang, Silin
%A Ke-di, Zhang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F zhang-etal-2026-cores
%X Text-to-SQL aims to bridge the gap between human intent and relational databases. While LLMs have shown proficiency in generating simple SQL queries, they struggle with complex analytical tasks. Moreover, models fine-tuned on SQL generation often suffer from catastrophic forgetting, which lose the versatility of procedural reasoning and pertaining to generation constraints. Inspired by the usage of high-resource programming languages as LLM reasoning intermediaries, we propose CORES model, which leverages Python as a procedural reasoning pivot to enhance both complex SQL generation and tabular reasoning. It decomposes complex queries into Python reasoning traces before generating the final SQL, which bridges the gap between procedural reasoning and declarative expression. In order to internalize this reasoning capability, we fine-tune LLMs via GRPO with tailored process reward functions that mitigate the sparse feedback problem. We experimentally verify the effectiveness of CORES on six text-to-SQL benchmarks, where ours outperforms baselines by 6.44% on average, while maintains good capability on three tableQA benchmarks.
%U https://aclanthology.org/2026.findings-acl.237/
%P 4827-4847
Markdown (Informal)
[CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA](https://aclanthology.org/2026.findings-acl.237/) (Zhang et al., Findings 2026)
ACL
- Meng Zhang, Ruochun Jin, Yuanxi Peng, Wenjing Yang, Haotian Wang, Liting Sun, Kun Hu, Silin Yang, and Zhang Ke-di. 2026. CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA. In Findings of the Association for Computational Linguistics: ACL 2026, pages 4827–4847, San Diego, California, United States. Association for Computational Linguistics.