CoSQL

CoSQL is a dataset used to evaluate the performance of models in multi-turn Text-to-SQL tasks, containing complex interactions that require handling context information and dynamic schema linking.

Papers using CoSQL (12)

Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL2026Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL2026MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training2025IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation2020 · 43 citesHIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing2022 · 32 citesDecoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL2021 · 20 citesPICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models2021 · 4 citesA Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges2024 · 2 citesSTAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing2022 · 1 citesCoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions2024 · 1 citesTowards Generalizable and Robust Text-to-SQL Parsing2022MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL2022