mlsanityData to 7 Oct 2026

MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL

arXiv 2608.09588 ↗First posted 10 Aug 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Traditional Text-to-SQL research and benchmarks assume a known target database, overlooking settings in which a query must be routed within a large, heterogeneous database collection. We therefore study schema linking in a multi-database setting, where the system must first locate the target database and then construct a compact, SQL-relevant schema for generation. We propose MDB-Link, a hierarchical schema-linking framework that retrieves question-relevant columns from a global index, aggregates retrieval evidence to shortlist databases, and uses a budget-aware large language model (LLM) for database reranking, table selection, and column grounding. With Qwen2.5-14B, MDB-Link outperforms LinkAlign on MMQA, Spider2-Snow, and BIRD-dev in database localization and column selection while producing schema subsets close in size to the gold schemas. Exact match improves from 16.88 to 51.41 on MMQA, 2.50 to 9.17 on Spider2-Snow, and 12.52 to 38.01 on BIRD-dev. MDB-Link also runs faster than LinkAlign and AutoLink, demonstrating the effectiveness of hierarchical schema reduction for downstream SQL generation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 56 references that are in the map. First posted on arXiv 10 Aug 2026.

Builds on

19 of 56 references.

References · 19

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  4. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  7. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  8. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  9. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  10. 2022Prompting GPT-3 To Be Reliablecited by 258
  11. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  12. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
7 more
  1. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  2. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  3. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Explorationcited by 34
  4. 2025LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQLcited by 26
  5. 2023SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Datacited by 16
  6. 2025AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scalecited by 15
  7. 2025SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databasescited by 3

Built on by

Not cited yet.