# Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation

arXiv: https://arxiv.org/abs/2402.17144 · HTML: https://mlsanity.com/paper/2402.17144/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 74 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 30 of 53)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [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)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation](https://mlsanity.com/paper/1905.08205/) (2019)
- [Multi-Stage Document Ranking with BERT](https://mlsanity.com/paper/1910.14424/) (2019)
- [RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL](https://mlsanity.com/paper/2302.05965/) (2023)
- [GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing](https://mlsanity.com/paper/2009.13845/) (2020)
- [SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning](https://mlsanity.com/paper/1711.04436/) (2017)
- [Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2012.12627/) (2020)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations](https://mlsanity.com/paper/2106.01093/) (2021)
- [A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability](https://mlsanity.com/paper/2303.13547/) (2023)

## Built on by (most cited first, 17 of 17)

- [Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL](https://mlsanity.com/paper/2406.08426/) (2024)
- [A Survey on Employing Large Language Models for Text-to-SQL Tasks](https://mlsanity.com/paper/2407.15186/) (2024)
- [A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?](https://mlsanity.com/paper/2408.05109/) (2024)
- [PURPLE: Making a Large Language Model a Better SQL Writer](https://mlsanity.com/paper/2403.20014/) (2024)
- [Text2Cypher: Bridging Natural Language and Graph Databases](https://mlsanity.com/paper/2412.10064/) (2024)
- [Reliable Text-to-SQL with Adaptive Abstention](https://mlsanity.com/paper/2501.10858/) (2025)
- [From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems](https://mlsanity.com/paper/2410.01066/) (2024)
- [LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models](https://mlsanity.com/paper/2504.02327/) (2025)
- [Enhancing Text2Cypher with Schema Filtering](https://mlsanity.com/paper/2505.05118/) (2025)
- [Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities](https://mlsanity.com/paper/2505.23838/) (2025)
- [Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task](https://mlsanity.com/paper/2506.11986/) (2025)
- [Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL Queries](https://mlsanity.com/paper/2506.23071/) (2025)
- [OsmT: Bridging OpenStreetMap Queries and Natural Language with Open-source Tag-aware Language Models](https://mlsanity.com/paper/2512.04738/) (2025)
- [Accurate Table Question Answering with Accessible LLMs](https://mlsanity.com/paper/2601.03137/) (2026)
- [Database Context Compression for Text-to-SQL on Real-World Large Databases](https://mlsanity.com/paper/2606.28601/) (2026)
- [Benchmarking Text-to-SQL under Role-Based Access Control](https://mlsanity.com/paper/2607.22115/) (2026)
- [LIMIT: Less Is More for Instruction Tuning in Text-to-SQL](https://mlsanity.com/paper/2609.24186/) (2026)

## Abstract (arXiv)

The Natural Language Interface to Databases (NLIDB) empowers non-technical users with database access through intuitive natural language (NL) interactions. Advanced approaches, utilizing neural sequence-to-sequence models or large-scale language models, typically employ auto-regressive decoding to generate unique SQL queries sequentially. While these translation models have greatly improved the overall translation accuracy, surpassing 70% on NLIDB benchmarks, the use of auto-regressive decoding to generate single SQL queries may result in sub-optimal outputs, potentially leading to erroneous translations. In this paper, we propose Metasql, a unified generate-then-rank framework that can be flexibly incorporated with existing NLIDBs to consistently improve their translation accuracy. Metasql introduces query metadata to control the generation of better SQL query candidates and uses learning-to-rank algorithms to retrieve globally optimized queries. Specifically, Metasql first breaks down the meaning of the given NL query into a set of possible query metadata, representing the basic concepts of the semantics. These metadata are then used as language constraints to steer the underlying translation model toward generating a set of candidate SQL queries. Finally, Metasql ranks the candidates to identify the best matching one for the given NL query. Extensive experiments are performed to study Metasql on two public NLIDB benchmarks. The results show that the performance of the translation models can be effectively improved using Metasql.