Text-To-SQL
135 papers with code • 6 benchmarks • 14 datasets
Text-to-SQL is a task in natural language processing (NLP) where the goal is to automatically generate SQL queries from natural language text. The task involves converting the text input into a structured representation and then using this representation to generate a semantically correct SQL query that can be executed on a database.
( Image credit: SyntaxSQLNet )
Benchmarks
These leaderboards are used to track progress in Text-To-SQL
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Text-To-SQL models and implementationsDatasets
Spider-Realistic
SParC
CoSQL
KaggleDBQA
SEDE
MultiSpider
Latest papers
Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL
We introduce two new methods, Dubo-SQL v1 and v2.
Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models
The recent breakthroughs in large language models (LLMs) are positioned to transition many areas of software.
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition
Table reasoning is a challenging task that requires understanding both natural language questions and structured tabular data.
PET-SQL: A Prompt-enhanced Two-stage Text-to-SQL Framework with Cross-consistency
Then, in the first stage, question-SQL pairs are retrieved as few-shot demonstrations, prompting the LLM to generate a preliminary SQL (PreSQL).
CodeS: Towards Building Open-source Language Models for Text-to-SQL
To address the limitations, we introduce CodeS, a series of pre-trained language models with parameters ranging from 1B to 15B, specifically designed for the text-to-SQL task.
Understanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench Benchmark
This study provides an in-depth analysis of the distribution and types of noise in the widely used BIRD-Bench benchmark and the impact of noise on models.
When is Tree Search Useful for LLM Planning? It Depends on the Discriminator
osu-nlp-group/llm-planning-eval
•
•
In this paper, we examine how large language models (LLMs) solve multi-step problems under a language agent framework with three components: a generator, a discriminator, and a planning method.
Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm
To improve the contextual learning capabilities of LLMs in text-to-SQL, a workflow paradigm method is proposed, aiming to enhance the attention and problem-solving scope of LLMs through decomposition.
Improving Generalization in Semantic Parsing by Increasing Natural Language Variation
Text-to-SQL semantic parsing has made significant progress in recent years, with various models demonstrating impressive performance on the challenging Spider benchmark.
AraSpider: Democratizing Arabic-to-SQL
The results showed that using back translation significantly improved the performance of both ChatGPT 3. 5 and SQLCoder models, which are considered top performers on the Spider dataset.
