There is currently a significant gap between the performance of fine-tuned models and
prompting approaches using Large Language Models (LLMs) on the challenging task of text …

To bridge the gap between users and data, numerous text-to-SQL systems have been
developed that allow users to pose natural language questions over relational databases …

We present Spider, a large-scale, complex and cross-domain semantic parsing and text-to-
SQL dataset annotated by 11 college students. It consists of 10,181 questions and 5,693 …

We present a neural approach called IRNet for complex and cross-domain Text-to-SQL.
IRNet aims to address two challenges: 1) the mismatch between intents expressed in natural …

Synthesizing SQL queries from natural language is a long-standing open problem and has
been attracting considerable interest recently. Toward solving the problem, the de facto …

To be informative, an evaluation must measure how well systems generalize to realistic
unseen data. We identify limitations of and propose improvements to current evaluations of …

This paper presents a new technique for automatically synthesizing SQL queries from
natural language (NL). At the core of our technique is a new NL-based program synthesis …

Interacting with relational databases through natural language helps users of any
background easily query and analyze a vast amount of data. This requires a system that …

Natural language has been the holy grail of query interface designers, but has generally
been considered too hard to work with, except in limited specific circumstances. In this …

Most existing studies in text-to-SQL tasks do not require generating complex SQL queries
with multiple clauses or sub-queries, and generalizing to new, unseen databases. In this …