Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL

• URL: http://arxiv.org/abs/2603.05996v1
• Date: Fri, 06 Mar 2026 07:57:06 GMT
• Title: Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL
• Abstract summary: Generative language models' performance does not extend equivalently to multi-turn Text-to-sourced.<n>We propose Track-, which enhances generative language models with dual-extractive modules designed to track schema and contextual changes in multi-turn Text-to-sourced.<n>Track- significantly improves execution accuracy in multi-turn interactions by 7.1% and 9.55% on datasets, respectively.
• Score: 50.84251174559123
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactions [2.9405869906238196]
  We explore interactions between several NL2 pipeline extensions to inspire development of more lightweight models.<n>We integrate the Nat intermediate representation, include a preprocessing step and a fine-tuning step based on synthetic data, and develop a novel reranker model.<n>We find that simply combining all of them does not lead to best results, but that their impact depends on their interactions with the baseline system.
  arXiv  Detail & Related papers  (2026-07-12T20:30:50Z)
• SQaLe: A Large Text-to-SQL Corpus Grounded in Real Schemas [2.905751301655124]
  Key bottleneck for developing text-to-hugging models is lack of large-scale datasets with sufficient schema and query complexity, domain coverage, and task diversity.<n>We introduce SQaLe: a large-scale semi-synthetic text-to-hugging dataset built on 135,875 relational database schemas expanded from a collection of real-world schemas,Pile.<n>SQaLe captures realistic schema size variability, diverse query patterns, and natural language ambiguity while maintaining execution validity.
  arXiv  Detail & Related papers  (2025-12-16T09:15:10Z)
• Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation [54.53145282349042]
  We introduce DSR-sourced, a textbfDual-textbfS textbfReasoning framework that models Text-to-context as an interaction between an adaptive context state and a progressive generation state.<n>Without any post-training or in-context examples, DSR-sourced achieves competitive performance, reaching 35.28% execution accuracy on Spider 2.0-Snow and 68.32% on BIRD development set.
  arXiv  Detail & Related papers  (2025-11-26T13:52:50Z)
• LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correction [5.123751486259634]
  We introduce LitE-, a Lightweight and Efficient framework with two components.<n>On BIRD, LitE- achieves 72.10% execution accuracy, and on Spider it reaches 88.45%, demonstrating comparable or superior performance to Retriever.<n>Our findings demonstrate that high-quality Text-to-correction generation is feasible with lightweight models, offering a practical solution for privacy-sensitive and resource-constrained settings.
  arXiv  Detail & Related papers  (2025-10-10T05:27:47Z)
• X-SQL: Expert Schema Linking and Understanding of Text-to-SQL with Multi-LLMs [0.0]
  We find that database schema information plays a significant or even dominant role in the Text-to-Admin task.<n>We introduce X-Supervised Finetuning (SFT) that achieves superior Linking results compared to existing open-source Text-to-Admin methods.<n>In addition, we propose an X- component that focuses on Understanding by bridging the gap between abstract information and the user's natural language question.
  arXiv  Detail & Related papers  (2025-09-07T02:51:43Z)
• RSL-SQL: Robust Schema Linking in Text-to-SQL Generation [51.00761167842468]
  We propose a novel framework called RSL- that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. benchmarks demonstrate that our approach achieves SOTA execution accuracy among open-source solutions, with 67.2% on BIRD and 87.9% on GPT-4ocorrection. Our approach outperforms a series of GPT-4 based Text-to-Seek systems when adopting DeepSeek (much cheaper) with same intact prompts.
  arXiv  Detail & Related papers  (2024-10-31T16:22:26Z)
• SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data [54.69489315952524]
  "Prompt" is designed to improve the few-shot prompting capabilities of Text-to-LLMs. "Prompt" outperforms previous approaches for in-context learning with few labeled data by a large margin. We show that emphPrompt outperforms previous approaches for in-context learning with few labeled data by a large margin.
  arXiv  Detail & Related papers  (2023-11-06T05:24:06Z)
• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)
• UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL [48.21638676148253]
  We present UniSAr (Unified Structure-Aware Autoregressive Language Model), which benefits from using an off-the-shelf language model. Specifically, UniSAr extends existing autoregressive models to incorporate three non-invasive extensions to make them structure-aware.
  arXiv  Detail & Related papers  (2022-03-15T11:02:55Z)
• Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing [44.0348697408427]
  The task of multi-turn text-to- semantic parsing aims to translate natural language utterances in an interaction intosql queries. A graph relational network and a non-linear layer are designed to update the representations of these two states respectively. Experimental results on the challenging Co dataset demonstrate the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2020-12-09T11:59:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.