# CORE-T: COherent REtrieval of Tables for Text-to-SQL

arXiv: https://arxiv.org/abs/2601.13111 · HTML: https://mlsanity.com/paper/2601.13111/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 19 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows](https://mlsanity.com/paper/2411.07763/) (2024)
- [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021)
- [Open Domain Question Answering over Tables via Dense Retrieval](https://mlsanity.com/paper/2103.12011/) (2021)
- [Arctic-Embed 2.0: Multilingual Retrieval Without Compromise](https://mlsanity.com/paper/2412.04506/) (2024)
- [BEAVER: An Enterprise Benchmark for Text-to-SQL](https://mlsanity.com/paper/2409.02038/) (2024)
- [Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval](https://mlsanity.com/paper/2404.09889/) (2024)
- [Table Search Using a Deep Contextualized Language Model](https://mlsanity.com/paper/2005.09207/) (2020)
- [EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline](https://mlsanity.com/paper/2504.03598/) (2025)
- [WarpGate: A Semantic Join Discovery System for Cloud Data Warehouses](https://mlsanity.com/paper/2212.14155/) (2022)
- [Table Retrieval May Not Necessitate Table-specific Model Design](https://mlsanity.com/paper/2205.09843/) (2022)
- [Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method](https://mlsanity.com/paper/2501.18539/) (2025)
- [Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-Service Business Intelligence](https://mlsanity.com/paper/2504.11627/) (2025)
- [REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval](https://mlsanity.com/paper/2511.00805/) (2025)

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

- [JoinGR: Learning to Traverse Join Graphs for Table Retrieval](https://mlsanity.com/paper/2610.01064/) (2026)

## Abstract (arXiv)

Realistic text-to-SQL workflows often require joining multiple tables. As a result, accurately retrieving the relevant set of tables becomes a key bottleneck for end-to-end performance. We study an open-book setting where queries must be answered over large, heterogeneous table collections pooled from many sources, without clean scoping signals such as database identifiers. Here, dense retrieval (DR) achieves high recall but returns many distractors, while join-aware alternatives often rely on extra assumptions and/or incur high inference overhead. We propose CORE-T, a scalable, training-free framework that enriches tables with LLM-generated purpose metadata and pre-computes a lightweight table-compatibility cache. At inference time, DR returns top-K candidates; a single LLM call selects a coherent, joinable subset, and a two-step additive adjustment stage restores strongly compatible tables. Across Bird, Spider, MMQA, and Beaver, CORE-T improves over DR by up to 22.7 points in table-selection F1 while returning up to 40% fewer tables, and by up to 24.4 points in multi-table execution accuracy, and uses 1.64-4.20x fewer total selection tokens than LLM-intensive baselines.