# Exploring Multi-Table Retrieval Through Iterative Search

arXiv: https://arxiv.org/abs/2511.13418 · HTML: https://mlsanity.com/paper/2511.13418/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 13 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [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)
- [Open Domain Question Answering over Tables via Dense Retrieval](https://mlsanity.com/paper/2103.12011/) (2021)
- [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)
- [CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL](https://mlsanity.com/paper/2311.01173/) (2023)
- [DBCopilot: Natural Language Querying over Massive Databases via Schema Routing](https://mlsanity.com/paper/2312.03463/) (2023)
- [Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method](https://mlsanity.com/paper/2501.18539/) (2025)
- [MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL](https://mlsanity.com/paper/2402.10666/) (2024)
- [Redefining Information Retrieval of Structured Database via Large Language Models](https://mlsanity.com/paper/2405.05508/) (2024)

## Built on by (most cited first, 2 of 2)

- [Fine-Grained Table Retrieval Through the Lens of Complex Queries](https://mlsanity.com/paper/2603.07146/) (2026)
- [JoinGR: Learning to Traverse Join Graphs for Table Retrieval](https://mlsanity.com/paper/2610.01064/) (2026)

## Abstract (arXiv)

Open-domain question answering over datalakes requires retrieving and composing information from multiple tables, a challenging subtask that demands semantic relevance and structural coherence (e.g., joinability). While exact optimization methods like Mixed-Integer Programming (MIP) can ensure coherence, their computational complexity is often prohibitive. Conversely, simpler greedy heuristics that optimize for query coverage alone often fail to find these coherent, joinable sets. This paper frames multi-table retrieval as an iterative search process, arguing this approach offers advantages in scalability, interpretability, and flexibility. We propose a general framework and a concrete instantiation: a fast, effective Greedy Join-Aware Retrieval algorithm that holistically balances relevance, coverage, and joinability. Experiments across 5 NL2SQL benchmarks demonstrate that our iterative method achieves competitive retrieval performance compared to the MIP-based approach while being 4-400x faster depending on the benchmark and search space settings. This work highlights the potential of iterative heuristics for practical, scalable, and composition-aware retrieval.