Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2509.14507 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918285273989120 |
|---|---|
| author | Chen, Jian Chen, Zhenyan Hu, Xuming Zhou, Peilin Hua, Yining Fang, Han Choy, Cissy Hing Yee Ke, Xinmei Luo, Jingfeng Yuan, Zixuan |
| author_facet | Chen, Jian Chen, Zhenyan Hu, Xuming Zhou, Peilin Hua, Yining Fang, Han Choy, Cissy Hing Yee Ke, Xinmei Luo, Jingfeng Yuan, Zixuan |
| contents | Natural Language to SQL (NL2SQL) provides a new model-centric paradigm that simplifies database access for non-technical users by converting natural language queries into SQL commands. Recent advancements, particularly those integrating Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) reasoning, have made significant strides in enhancing NL2SQL performance. However, challenges such as inaccurate task decomposition and keyword extraction by LLMs remain major bottlenecks, often leading to errors in SQL generation. While existing datasets aim to mitigate these issues by fine-tuning models, they struggle with over-fragmentation of tasks and lack of domain-specific keyword annotations, limiting their effectiveness. To address these limitations, we present DeKeyNLU, a novel dataset which contains 1,500 meticulously annotated QA pairs aimed at refining task decomposition and enhancing keyword extraction precision for the RAG pipeline. Fine-tuned with DeKeyNLU, we propose DeKeySQL, a RAG-based NL2SQL pipeline that employs three distinct modules for user question understanding, entity retrieval, and generation to improve SQL generation accuracy. We benchmarked multiple model configurations within DeKeySQL RAG pipeline. Experimental results demonstrate that fine-tuning with DeKeyNLU significantly improves SQL generation accuracy on both BIRD (62.31% to 69.10%) and Spider (84.2% to 88.7%) dev datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14507 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction Chen, Jian Chen, Zhenyan Hu, Xuming Zhou, Peilin Hua, Yining Fang, Han Choy, Cissy Hing Yee Ke, Xinmei Luo, Jingfeng Yuan, Zixuan Artificial Intelligence Computation and Language Natural Language to SQL (NL2SQL) provides a new model-centric paradigm that simplifies database access for non-technical users by converting natural language queries into SQL commands. Recent advancements, particularly those integrating Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) reasoning, have made significant strides in enhancing NL2SQL performance. However, challenges such as inaccurate task decomposition and keyword extraction by LLMs remain major bottlenecks, often leading to errors in SQL generation. While existing datasets aim to mitigate these issues by fine-tuning models, they struggle with over-fragmentation of tasks and lack of domain-specific keyword annotations, limiting their effectiveness. To address these limitations, we present DeKeyNLU, a novel dataset which contains 1,500 meticulously annotated QA pairs aimed at refining task decomposition and enhancing keyword extraction precision for the RAG pipeline. Fine-tuned with DeKeyNLU, we propose DeKeySQL, a RAG-based NL2SQL pipeline that employs three distinct modules for user question understanding, entity retrieval, and generation to improve SQL generation accuracy. We benchmarked multiple model configurations within DeKeySQL RAG pipeline. Experimental results demonstrate that fine-tuning with DeKeyNLU significantly improves SQL generation accuracy on both BIRD (62.31% to 69.10%) and Spider (84.2% to 88.7%) dev datasets. |
| title | DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2509.14507 |