# CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL

arXiv: https://arxiv.org/abs/2311.01173 · HTML: https://mlsanity.com/paper/2311.01173/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 2 Nov 2023.

## Builds on (most cited first, 18 of 18)

- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [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)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [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)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [SGPT: GPT Sentence Embeddings for Semantic Search](https://mlsanity.com/paper/2202.08904/) (2022)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability](https://mlsanity.com/paper/2303.13547/) (2023)
- [Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data](https://mlsanity.com/paper/2106.05006/) (2021)
- [From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering](https://mlsanity.com/paper/2205.11729/) (2022)
- [Rethinking Label Smoothing on Multi-hop Question Answering](https://mlsanity.com/paper/2212.09512/) (2022)

## Built on by (most cited first, 24 of 24)

- [A Survey on Employing Large Language Models for Text-to-SQL Tasks](https://mlsanity.com/paper/2407.15186/) (2024)
- [ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration](https://mlsanity.com/paper/2502.00675/) (2025)
- [A Survey of Table Reasoning with Large Language Models](https://mlsanity.com/paper/2402.08259/) (2024)
- [An Audit on the Perspectives and Challenges of Hallucinations in NLP](https://mlsanity.com/paper/2404.07461/) (2024)
- [Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL](https://mlsanity.com/paper/2511.10192/) (2025)
- [MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL](https://mlsanity.com/paper/2402.10666/) (2024)
- [DAC: Decomposed Automation Correction for Text-to-SQL](https://mlsanity.com/paper/2408.08779/) (2024)
- [Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions](https://mlsanity.com/paper/2506.11111/) (2025)
- [Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities](https://mlsanity.com/paper/2505.23838/) (2025)
- [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)
- [Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence](https://mlsanity.com/paper/2507.10281/) (2025)
- [PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning](https://mlsanity.com/paper/2509.07159/) (2025)
- [Exploring Multi-Table Retrieval Through Iterative Search](https://mlsanity.com/paper/2511.13418/) (2025)
- [Human Centered AI for Indian Legal Text Analytics](https://mlsanity.com/paper/2403.10944/) (2024)
- [CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description](https://mlsanity.com/paper/2508.12769/) (2025)
- [DynaQuery: A Self-Adapting Framework for Querying Structured and Multimodal Data](https://mlsanity.com/paper/2510.18029/) (2025)
- [Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding](https://mlsanity.com/paper/2604.28028/) (2026)
- [Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method](https://mlsanity.com/paper/2605.18766/) (2026)
- [CAPER: Clause-Aligned Process Supervision for Text-to-SQL](https://mlsanity.com/paper/2606.03327/) (2026)
- [Database Context Compression for Text-to-SQL on Real-World Large Databases](https://mlsanity.com/paper/2606.28601/) (2026)
- [REALMS: An AI-Assistant Conversational System for Real-Time Exact Audience Sizing over High-Dimensional Nested Profiles](https://mlsanity.com/paper/2609.30547/) (2026)
- [BudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQL](https://mlsanity.com/paper/2610.00092/) (2026)
- [LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement](https://mlsanity.com/paper/2610.14777/) (2026)

## Abstract (arXiv)

Existing Text-to-SQL generators require the entire schema to be encoded with the user text. This is expensive or impractical for large databases with tens of thousands of columns. Standard dense retrieval techniques are inadequate for schema subsetting of a large structured database, where the correct semantics of retrieval demands that we rank sets of schema elements rather than individual elements. In response, we propose a two-stage process for effective coverage during retrieval. First, we instruct an LLM to hallucinate a minimal DB schema deemed adequate to answer the query. We use the hallucinated schema to retrieve a subset of the actual schema, by composing the results from multiple dense retrievals. Remarkably, hallucination unicodex2013 generally considered a nuisance unicodex2013 turns out to be actually useful as a bridging mechanism. Since no existing benchmarks exist for schema subsetting on large databases, we introduce three benchmarks. Two semi-synthetic datasets are derived from the union of schemas in two well-known datasets, SPIDER and BIRD, resulting in 4502 and 798 schema elements respectively. A real-life benchmark called SocialDB is sourced from an actual large data warehouse comprising 17844 schema elements. We show that our method1 leads to significantly higher recall than SOTA retrieval-based augmentation methods.