<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhai-etal-2025-optimizing">
    <titleInfo>
        <title>Optimizing Reasoning for Text-to-SQL with Execution Feedback</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bohan</namePart>
        <namePart type="family">Zhai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Canwen</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuxiong</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhewei</namePart>
        <namePart type="family">Yao</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>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</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">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Text-to-SQL demands precise reasoning to convert natural language questions into structured queries. While large language models (LLMs) excel in many reasoning tasks, their ability to leverage Chain-of-Thought (CoT) reasoning for text-to-SQL remains underexplored. We identify critical limitations: zero-shot CoT offers minimal gains, and Direct Preference Optimization (DPO) applied without CoT yields marginal improvements. We propose ExCoT-DPO, a novel framework that iteratively optimizes open-source LLMs by combining CoT reasoning with off-policy and on-policy DPO, relying solely on execution accuracy as feedback. This approach eliminates the need for reward models or human-annotated preferences. Our experimental results demonstrate significant performance gains: ExCoT-DPO improves execution accuracy on BIRD from 57.37% to 68.51% and on Spider from 78.81% to 86.59% for LLaMA-3 70B, with Qwen-2.5-Coder demonstrating similar improvements. Our best model achieves state-of-the-art performance in the single-model setting on both BIRD and Spider datasets.</abstract>
    <identifier type="citekey">zhai-etal-2025-optimizing</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.982</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.982/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>19206</start>
            <end>19218</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Optimizing Reasoning for Text-to-SQL with Execution Feedback
%A Zhai, Bohan
%A Xu, Canwen
%A He, Yuxiong
%A Yao, Zhewei
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F zhai-etal-2025-optimizing
%X Text-to-SQL demands precise reasoning to convert natural language questions into structured queries. While large language models (LLMs) excel in many reasoning tasks, their ability to leverage Chain-of-Thought (CoT) reasoning for text-to-SQL remains underexplored. We identify critical limitations: zero-shot CoT offers minimal gains, and Direct Preference Optimization (DPO) applied without CoT yields marginal improvements. We propose ExCoT-DPO, a novel framework that iteratively optimizes open-source LLMs by combining CoT reasoning with off-policy and on-policy DPO, relying solely on execution accuracy as feedback. This approach eliminates the need for reward models or human-annotated preferences. Our experimental results demonstrate significant performance gains: ExCoT-DPO improves execution accuracy on BIRD from 57.37% to 68.51% and on Spider from 78.81% to 86.59% for LLaMA-3 70B, with Qwen-2.5-Coder demonstrating similar improvements. Our best model achieves state-of-the-art performance in the single-model setting on both BIRD and Spider datasets.
%R 10.18653/v1/2025.findings-acl.982
%U https://aclanthology.org/2025.findings-acl.982/
%U https://doi.org/10.18653/v1/2025.findings-acl.982
%P 19206-19218

Markdown (Informal)

[Optimizing Reasoning for Text-to-SQL with Execution Feedback](https://aclanthology.org/2025.findings-acl.982/) (Zhai et al., Findings 2025)

• Optimizing Reasoning for Text-to-SQL with Execution Feedback (Zhai et al., Findings 2025)

ACL

• Bohan Zhai, Canwen Xu, Yuxiong He, and Zhewei Yao. 2025. Optimizing Reasoning for Text-to-SQL with Execution Feedback. In Findings of the Association for Computational Linguistics: ACL 2025, pages 19206–19218, Vienna, Austria. Association for Computational Linguistics.