Bird

The 'Bird' dataset is a benchmark used to evaluate the performance of text-to-SQL models in translating natural language questions into SQL queries, particularly focusing on complex queries.

Papers using Bird (9)

Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning2026DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL2026How Far Do On-Prem Open LLMs Get on Text-to-SQL? A Cross-Family Size x Technique Frontier on BIRD2026Test-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 citesFGTR: Fine-Grained Multi-Table Retrieval via Hierarchical LLM Reasoning2026Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL2025Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL2024 · 1 cites