让大模型更懂多轮对话中的数据库结构和上下文变化
Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL
- 用双提取模块分别跟踪数据库模式和对话上下文变化
- 在SparC和CoSQL上多轮准确率提升7.1%和9.55%
- 适合做多轮自然语言转SQL的开发者和研究者
生成式语言模型在单轮Text-to-SQL中表现良好，但在多轮场景下性能下降明显，主要因难以处理上下文信息和动态数据库模式关联。本文提出Track-SQL框架，通过引入语义增强的模式提取器和模式感知的上下文提取器，实现对多轮交互中模式与上下文变化的精准追踪。实验表明，Track-SQL在SparC和CoSQL数据集上达到当前最优性能，多轮执行准确率分别提升7.1%和9.55%。代码将开源。
原文摘要 · Abstract (English)
Generative language models have shown significant potential in single-turn Text-to-SQL. However, their performance does not extend equivalently to multi-turn Text-to-SQL. This is primarily due to generative language models' inadequacy in handling the complexities of context information and dynamic schema linking in multi-turn interactions. In this paper, we propose a framework named Track-SQL, which enhances generative language models with dual-extractive modules designed to track schema and contextual changes in multi-turn Text-to-SQL. Specifically, Track-SQL incorporates a \emph{Semantic-enhanced Schema Extractor} and a \emph{Schema-aware Context Extractor}. Experimental results demonstrate that Track-SQL achieves state-of-the-art performance on the SparC and CoSQL datasets. Furthermore, detailed ablation studies reveal that Track-SQL significantly improves execution accuracy in multi-turn interactions by 7.1\% and 9.55\% on these datasets, respectively. Our implementation will be open-sourced at https://github.com/DMIRLAB-Group/Track-SQL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。