FERN: Cross-Benchmark Table Retrieval for Text-to-SQL with Frozen Retrievers and Learned Ranking
cs.IR, cs.CL
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/tobymao/sqlglot
Terminology
Sources
- BEAVER: An Enterprise Benchmark for Text-to-SQL
- RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL
- Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards
- The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models
- Introducing LETOR 4.0 Datasets
- NIFT-SQL: Customer-Supervised Table Scoring for Enterprise Text-to-SQL Retrieval
- CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale
- CORE-T: COherent REtrieval of Tables for Text-to-SQL
- CHESS: Contextual Harnessing for Efficient SQL Synthesis
- DBCopilot: Natural Language Querying over Massive Databases via Schema Routing
- Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA