Spider

Dataset Card for Spider Dataset Summary Spider is a large-scale complex and cross-domain semantic parsing and text-to-SQL dataset annotated by 11 Yale students. The goal of the Spider challenge is to develop natural language interfaces to cross-domain databases. Supported Tasks and Leaderboards The leaderboard can be s

Papers using Spider (10)

Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning2026DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL2026T2D-Bench: Evidence-Gated Evaluation of LLM Outputs for Type 2 Diabetes Using a Multi-Layer Clinical-Lifestyle Knowledge Graph2026Test-Time Verification for Text-to-SQL via Outcome Reward Models2026JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling2025 · 1 citesS0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models2026FGTR: Fine-Grained Multi-Table Retrieval via Hierarchical LLM Reasoning2026LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures2025DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph2025Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL2024 · 1 cites