# Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics

arXiv: https://arxiv.org/abs/2606.28387 · HTML: https://mlsanity.com/paper/2606.28387/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows](https://mlsanity.com/paper/2411.07763/) (2024)
- [MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL](https://mlsanity.com/paper/2312.11242/) (2023)
- [Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data](https://mlsanity.com/paper/2106.05006/) (2021)
- [The Amazon Nova Family of Models: Technical Report and Model Card](https://mlsanity.com/paper/2506.12103/) (2025)
- [LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL](https://mlsanity.com/paper/2503.18596/) (2025)
- [Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers](https://mlsanity.com/paper/2506.00054/) (2025)
- [AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale](https://mlsanity.com/paper/2511.17190/) (2025)
- [Extractive Schema Linking for Text-to-SQL](https://mlsanity.com/paper/2501.17174/) (2025)
- [Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL](https://mlsanity.com/paper/2412.12522/) (2024)
- [Permissioned LLMs: Enforcing Access Control in Large Language Models](https://mlsanity.com/paper/2505.22860/) (2025)
- [Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems](https://mlsanity.com/paper/2606.01416/) (2026)
- [RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL](https://mlsanity.com/paper/2507.23104/) (2025)
- [Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQL](https://mlsanity.com/paper/2510.14296/) (2025)
- [SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases](https://mlsanity.com/paper/2505.18363/) (2025)
- [Enterprise AI Must Enforce Participant-Aware Access Control](https://mlsanity.com/paper/2509.14608/) (2025)

## Built on by (most cited first, 1 of 1)

- [Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting](https://mlsanity.com/paper/2607.01457/) (2026)

## Abstract (arXiv)

Enterprise text-to-SQL systems often fail before SQL is generated: the model receives the wrong schema context. Modern warehouses contain thousands of tables, abbreviated columns, informal metrics, hidden join conventions, and permission boundaries that are not captured by raw table names. We introduce Schema-First Retrieval, a retrieval layer that embeds catalog metadata rather than warehouse rows. The system indexes five typed catalog objects, tables, columns, metrics, relationships, and query history, using object-specific text templates. At query time, it combines parallel vector search, lineage expansion, cross-encoder reranking, workload memory, and deterministic access-control gates before SQL generation. On CRUSH4SQL (1,534 questions), Schema-First Retrieval reaches 96.4% table recall@20 and cross-encoder reranking adds +11.1 points at column recall@10; against an equally-templated BM25 baseline, semantic retrieval is +32.8 points at table recall@5. On SEDE (857 questions), query history raises table recall@5 from 52.1% to 92.3%. On BIRD (96 questions), schema-first context reduces SQL execution errors from 15.6% to 6.2%, a 2.5x reduction. These results show that catalog selection is a first-class retrieval problem for natural language analytics, not a prompt formatting detail.