Results 211 to 220 of about 284,169 (264)

Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL

arXiv.org
Generating accurate SQL from users'natural language questions (text-to-SQL) remains a long-standing challenge due to the complexities involved in user question understanding, database schema comprehension, and SQL generation.
Zijin Hong, Zheng Yuan, Qinggang Zhang, Hao Chen, Junnan Dong, Feiran Huang, Xiao Huang   +6 more
semanticscholar   +1 more source

AutoSteer: Learned Query Optimization for Any SQL Database

Proceedings of the VLDB Endowment, 2023
This paper presents AutoSteer, a learning-based solution that automatically drives query optimization in any SQL database that exposes tunable optimizer knobs.
Christoph Anneser, N. Tatbul, David Cohen, Zhenggang Xu, N. Laptev, Ryan Marcus, P. Pandian, Ryan Marcus. AutoSteer   +7 more
semanticscholar   +1 more source

Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

International Conference on Learning Representations
Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operations from data transformation to analytics.
Fangyu Lei, Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Hongcheng Gao, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, Tao Yu   +16 more
semanticscholar   +1 more source

Duplicates in SQL

Data & Knowledge Engineering, 1994
Abstract The relational database model is defined in terms of sets, whereas SQL needs the DISTINCT option for explicit duplicate removal. We define the underlying concept of duplicate tuples, generalize the operators of the relational algebra and study the connection with logic. It is shown that ‘baggy’ operators violate classical equivalences.
Kwast, K.L., van Denneheuvel, S.J.
openaire   +4 more sources

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

International Conference on Learning Representations
In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to improve candidate generation and ...
Mohammadreza Pourreza, Hailong Li, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, Sercan Ö. Arik   +9 more
semanticscholar   +1 more source

MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation

International Conference on Computational Linguistics
Recent advancements in large language models (LLMs) have enabled in-context learning (ICL)-based methods that significantly outperform fine-tuning approaches for text-to-SQL tasks. However, their performance is still considerably lower than that of human
Dongjun Lee, Choongwon Park, Jaehyuk Kim, Heesoo Park   +3 more
semanticscholar   +1 more source

SQL-Middleware: Enabling the Blockchain with SQL

2021
With the development of blockchain, blockchain has a broad prospect as a new type of data management system. However, limited to the data modeling method of blockchain, the usability of blockchain is restricted; In addition, every blockchain system has its own native but naive interfaces, when developing based on the different blockchain systems, which
Haibo Tang, Nan Jiang, Yingjie Yang, Zhao Zhang, Cheqing Jin, Wei Fan, Tong Xing, Gang Qin, Gao Yichen, Sijia Deng   +9 more
openaire   +2 more sources

The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models

arXiv.org
Schema linking is a crucial step in Text-to-SQL pipelines. Its goal is to retrieve the relevant tables and columns of a target database for a user's query while disregarding irrelevant ones.
Karime Maamari, Fadhil Abubaker, Daniel Jaroslawicz, Amine Mhedhbi   +3 more
semanticscholar   +1 more source

Synthesizing Text-to-SQL Data from Weak and Strong LLMs

Annual Meeting of the Association for Computational Linguistics
The capability gap between open-source and closed-source large language models (LLMs) remains a challenge in text-to-SQL tasks. In this paper, we introduce a synthetic data approach that combines data produced by larger, more powerful models (strong ...
Jiaxi Yang, Binyuan Hui, Min Yang, Jian Yang, Junyang Lin, Chang Zhou   +5 more
semanticscholar   +1 more source

Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation

Annual Meeting of the Association for Computational Linguistics
Large Language Models (LLMs) driven by In-Context Learning (ICL) have significantly improved the performance of text-to-SQL. Previous methods generally employ a two-stage reasoning framework, namely 1) schema linking and 2) logical synthesis, making the ...
Ge Qu, Jinyang Li, Bowen Li, Bowen Qin, Nan Huo, Chenhao Ma, Reynold Cheng   +6 more
semanticscholar   +1 more source