|
| 1 | +<!DOCTYPE html> |
| 2 | +<html> |
| 3 | +<head> |
| 4 | + <meta charset="utf-8"> |
| 5 | + <!-- Meta tags for social media banners, these should be filled in appropriatly as they are your "business card" --> |
| 6 | + <!-- Replace the content tag with appropriate information --> |
| 7 | + <meta name="description" content="SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning"> |
| 8 | + <meta property="og:title" content="SQL-R1"/> |
| 9 | + <meta property="og:description" content="Training Natural Language to SQL Reasoning Model By Reinforcement Learning"/> |
| 10 | + <meta property="og:url" content="https://github.com/MPX0222/SQL-R1"/> |
| 11 | + <!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X630--> |
| 12 | + <meta property="og:image" content="static/image/your_banner_image.png" /> |
| 13 | + <meta property="og:image:width" content="1200"/> |
| 14 | + <meta property="og:image:height" content="630"/> |
| 15 | + |
| 16 | + |
| 17 | + <meta name="twitter:title" content="TWITTER BANNER TITLE META TAG"> |
| 18 | + <meta name="twitter:description" content="TWITTER BANNER DESCRIPTION META TAG"> |
| 19 | + <!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X600--> |
| 20 | + <meta name="twitter:image" content="static/images/your_twitter_banner_image.png"> |
| 21 | + <meta name="twitter:card" content="summary_large_image"> |
| 22 | + <!-- Keywords for your paper to be indexed by--> |
| 23 | + <meta name="keywords" content="KEYWORDS SHOULD BE PLACED HERE"> |
| 24 | + <meta name="viewport" content="width=device-width, initial-scale=1"> |
| 25 | + |
| 26 | + |
| 27 | + <title>SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning</title> |
| 28 | + <!-- <link rel="icon" type="image/x-icon" href="static/images/favicon.ico"> --> |
| 29 | + <link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" |
| 30 | + rel="stylesheet"> |
| 31 | + |
| 32 | + <link rel="stylesheet" href="static/css/bulma.min.css"> |
| 33 | + <link rel="stylesheet" href="static/css/bulma-carousel.min.css"> |
| 34 | + <link rel="stylesheet" href="static/css/bulma-slider.min.css"> |
| 35 | + <link rel="stylesheet" href="static/css/fontawesome.all.min.css"> |
| 36 | + <link rel="stylesheet" |
| 37 | + href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css"> |
| 38 | + <link rel="stylesheet" href="static/css/index.css"> |
| 39 | + |
| 40 | + <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script> |
| 41 | + <script src="https://documentcloud.adobe.com/view-sdk/main.js"></script> |
| 42 | + <script defer src="static/js/fontawesome.all.min.js"></script> |
| 43 | + <script src="static/js/bulma-carousel.min.js"></script> |
| 44 | + <script src="static/js/bulma-slider.min.js"></script> |
| 45 | + <script src="static/js/index.js"></script> |
| 46 | +</head> |
| 47 | +<body> |
| 48 | + |
| 49 | + |
| 50 | + <section class="hero"> |
| 51 | + <div class="hero-body"> |
| 52 | + <div class="container is-max-desktop"> |
| 53 | + <div class="columns is-centered"> |
| 54 | + <div class="column has-text-centered"> |
| 55 | + <h1 class="title is-1 publication-title">SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning</h1> |
| 56 | + <div class="is-size-5 publication-authors"> |
| 57 | + <span class="author-block"> |
| 58 | + <a href="https://github.com/MPX0222" target="_blank">Peixian Ma</a><sup>1,2</sup>,</span> |
| 59 | + <span class="author-block"> |
| 60 | + <a href="#" target="_blank">Xialie Zhuang</a><sup>1,3</sup>,</span> |
| 61 | + <span class="author-block"> |
| 62 | + <a href="#" target="_blank">Chengjin Xu</a><sup>1,4</sup>,</span> |
| 63 | + <span class="author-block"> |
| 64 | + <a href="#" target="_blank">Xuhui Jiang</a><sup>1,4</sup>,</span> |
| 65 | + <span class="author-block"> |
| 66 | + <a href="#" target="_blank">Ran Chen</a><sup>1</sup>,</span> |
| 67 | + <span class="author-block"> |
| 68 | + <a href="#" target="_blank">Jian Guo</a><sup>1</sup> |
| 69 | + </span> |
| 70 | + </div> |
| 71 | + |
| 72 | + <div class="is-size-5 publication-authors"> |
| 73 | + <span class="author-block"> |
| 74 | + <sup>1</sup>IDEA Research, International Digital Economy Academy<br> |
| 75 | + <sup>2</sup>The Hong Kong University of Science and Technology (Guangzhou)<br> |
| 76 | + <sup>3</sup>University of Chinese Academy of Science<br> |
| 77 | + <sup>4</sup>DataArc Tech Ltd.<br> |
| 78 | + </span> |
| 79 | + <!-- <span class="eql-cntrb"><small><br><sup>*</sup>Indicates Equal Contribution</small></span> --> |
| 80 | + </div> |
| 81 | + |
| 82 | + <div class="column has-text-centered"> |
| 83 | + <div class="publication-links"> |
| 84 | + <span class="link-block"> |
| 85 | + <a href="https://arxiv.org/pdf/2504.08600.pdf" target="_blank" |
| 86 | + class="external-link button is-normal is-rounded is-dark"> |
| 87 | + <span class="icon"> |
| 88 | + <i class="fas fa-file-pdf"></i> |
| 89 | + </span> |
| 90 | + <span>Paper</span> |
| 91 | + </a> |
| 92 | + </span> |
| 93 | + |
| 94 | + <span class="link-block"> |
| 95 | + <a href="https://github.com/MPX0222/SQL-R1" target="_blank" |
| 96 | + class="external-link button is-normal is-rounded is-dark"> |
| 97 | + <span class="icon"> |
| 98 | + <i class="fab fa-github"></i> |
| 99 | + </span> |
| 100 | + <span>Code</span> |
| 101 | + </a> |
| 102 | + </span> |
| 103 | + |
| 104 | + <span class="link-block"> |
| 105 | + <a href="https://arxiv.org/abs/2504.08600" target="_blank" |
| 106 | + class="external-link button is-normal is-rounded is-dark"> |
| 107 | + <span class="icon"> |
| 108 | + <i class="ai ai-arxiv"></i> |
| 109 | + </span> |
| 110 | + <span>arXiv</span> |
| 111 | + </a> |
| 112 | + </span> |
| 113 | + </div> |
| 114 | + </div> |
| 115 | + </div> |
| 116 | + </div> |
| 117 | + </div> |
| 118 | + </div> |
| 119 | + </div> |
| 120 | +</section> |
| 121 | + |
| 122 | +<!-- Introduction Section --> |
| 123 | +<section class="section"> |
| 124 | + <div class="container is-max-desktop"> |
| 125 | + <div class="columns is-centered has-text-centered"> |
| 126 | + <div class="column is-four-fifths"> |
| 127 | + <h2 class="title is-3">Introduction</h2> |
| 128 | + <div class="content has-text-justified"> |
| 129 | + <p> |
| 130 | + Natural Language to SQL (NL2SQL) enables intuitive interactions with databases by transforming natural language queries into structured SQL statements. Despite recent advancements in enhancing human-computer interaction within database applications, significant challenges persist, particularly regarding the inference performance in complex scenarios involving multi-table joins and nested queries. |
| 131 | + </p> |
| 132 | + <p> |
| 133 | + Current methodologies primarily utilize supervised fine-tuning (SFT) to train the NL2SQL model, which may limit adaptability and interpretability in new environments (e.g., finance and healthcare). In order to enhance the reasoning performance of the NL2SQL model in the above complex situations, we introduce SQL-R1, a novel NL2SQL reasoning model trained by the reinforcement learning (RL) algorithms. |
| 134 | + </p> |
| 135 | + <div class="columns is-centered has-text-centered"> |
| 136 | + <div class="column"> |
| 137 | + <img src="images/overview.png" alt="SQL-R1 Overview" style="width: 100%; height: auto;"/> |
| 138 | + </div> |
| 139 | + </div> |
| 140 | + </div> |
| 141 | + </div> |
| 142 | + </div> |
| 143 | + </div> |
| 144 | +</section> |
| 145 | + |
| 146 | +<!-- Experiment Section --> |
| 147 | +<section class="section"> |
| 148 | + <div class="container is-max-desktop"> |
| 149 | + <div class="columns is-centered has-text-centered"> |
| 150 | + <div class="column is-four-fifths"> |
| 151 | + <h2 class="title is-3">Experiments</h2> |
| 152 | + <div class="columns is-centered has-text-centered"> |
| 153 | + <div class="column"> |
| 154 | + <img src="images/table1.png" alt="Experiment Results" style="width: 100%; height: auto;"/> |
| 155 | + </div> |
| 156 | + </div> |
| 157 | + |
| 158 | + </div> |
| 159 | +</section> |
| 160 | + |
| 161 | +<!--BibTex citation --> |
| 162 | + <section class="section" id="BibTeX"> |
| 163 | + <div class="container is-max-desktop content"> |
| 164 | + <h2 class="title">BibTeX</h2> |
| 165 | + <pre><code>@article{ma2025sql, |
| 166 | + title={SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning}, |
| 167 | + author={Ma, Peixian and Zhuang, Xialie and Xu, Chengjin and Jiang, Xuhui and Chen, Ran and Guo, Jian}, |
| 168 | + journal={arXiv preprint arXiv:2504.08600}, |
| 169 | + year={2025} |
| 170 | +}</code></pre> |
| 171 | + </div> |
| 172 | +</section> |
| 173 | +<!--End BibTex citation --> |
| 174 | + |
| 175 | + |
| 176 | + <footer class="footer"> |
| 177 | + <div class="container"> |
| 178 | + <div class="columns is-centered"> |
| 179 | + <div class="column is-8"> |
| 180 | + <div class="content"> |
| 181 | + |
| 182 | + <p> |
| 183 | + This page was built using the <a href="https://github.com/eliahuhorwitz/Academic-project-page-template" target="_blank">Academic Project Page Template</a> which was adopted from the <a href="https://nerfies.github.io" target="_blank">Nerfies</a> project page. |
| 184 | + You are free to borrow the source code of this website, we just ask that you link back to this page in the footer. <br> This website is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/" target="_blank">Creative |
| 185 | + Commons Attribution-ShareAlike 4.0 International License</a>. |
| 186 | + </p> |
| 187 | + |
| 188 | + </div> |
| 189 | + </div> |
| 190 | + </div> |
| 191 | + </div> |
| 192 | +</footer> |
| 193 | + |
| 194 | +<!-- Statcounter tracking code --> |
| 195 | + |
| 196 | +<!-- You can add a tracker to track page visits by creating an account at statcounter.com --> |
| 197 | + |
| 198 | + <!-- End of Statcounter Code --> |
| 199 | + |
| 200 | + </body> |
| 201 | + </html> |
0 commit comments