Related papers: PolySQL: Scaling Text-to-SQL Evaluation Across SQL…
Text-to-SQL models, which parse natural language (NL) questions to executable SQL queries, are increasingly adopted in real-world applications. However, deploying such models in the real world often requires adapting them to the highly…
The Natural Language to SQL (NL2SQL) technique is used to convert natural language queries into executable SQL statements. Typically, slot-filling is employed as a classification method for multi-task cases to achieve this goal. However,…
We perform an empirical evaluation of Text-to-SQL capabilities of the Codex language model. We find that, without any finetuning, Codex is a strong baseline on the Spider benchmark; we also analyze the failure modes of Codex in this…
Natural Language to SQL (i.e., NL2SQL) translation is crucial for democratizing database access, but even state-of-the-art models frequently generate semantically incorrect SQL queries, hindering the widespread adoption of these techniques…
Recently, Text-to-SQL for multi-turn dialogue has attracted great interest. Here, the user input of the current turn is parsed into the corresponding SQL query of the appropriate database, given all previous dialogue history. Current…
Analytical SQL is widely used in modern database applications and data analysis. However, its partitioning and grouping operators are challenging for novice users. Unfortunately, programming by example, shown effective on standard SQL, are…
Recent text-to-SQL systems powered by large language models (LLMs) have demonstrated remarkable performance in translating natural language queries into SQL. However, these systems often struggle with complex database structures and…
Text-to-SQL aims to map natural language questions to SQL queries. The sketch-based method combined with execution-guided (EG) decoding strategy has shown a strong performance on the WikiSQL benchmark. However, execution-guided decoding…
Relational databases are foundational to numerous domains, including business intelligence, scientific research, and enterprise systems. However, accessing and analyzing structured data often requires proficiency in SQL, which is a skill…
Text-to-SQL systems often struggle with deep contextual understanding, particularly for complex queries with subtle requirements. We present PV-SQL, an agentic framework that addresses these failures through two complementary components:…
Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environments where databases contain hundreds of tables with massive noisy metadata. Rather than…
Large Language Models (LLMs) exhibit impressive problem-solving skills across many tasks, but they still underperform compared to humans in various downstream applications, such as text-to-SQL. On the BIRD benchmark leaderboard, human…
We introduce SQL-Exchange, a framework for mapping SQL queries across different database schemas by preserving the source query structure while adapting domain-specific elements to align with the target schema. We investigate the conditions…
We present a novel symbolic reasoning engine for SQL which can efficiently generate an input $I$ for $n$ queries $P_1, \cdots, P_n$, such that their outputs on $I$ satisfy a given property (expressed in SMT). This is useful in different…
Querying a relational database is difficult because it requires users to know both the SQL language and be familiar with the schema. On the other hand, many users possess enough domain familiarity or expertise to describe their desired…
Cross-lingual text representations have gained popularity lately and act as the backbone of many tasks such as unsupervised machine translation and cross-lingual information retrieval, to name a few. However, evaluation of such…
In recent years, the surge in unstructured data analysis, facilitated by advancements in Machine Learning (ML), has prompted diverse approaches for handling images, text documents, and videos. Analysts, leveraging ML models, can extract…
We present OraPlan-SQL, our system for the Archer NL2SQL Evaluation Challenge 2025, a bilingual benchmark requiring complex reasoning such as arithmetic, commonsense, and hypothetical inference. OraPlan-SQL ranked first, exceeding the…
Speech-based inputs have been gaining significant momentum with the popularity of smartphones and tablets in our daily lives, since voice is the most easiest and efficient way for human-computer interaction. This paper works towards…
The design of SQL is based on a three-valued logic (3VL), rather than the familiar Boolean logic. 3VL adds a truth value unknown to true and false to handle nulls. Viewed as indispensable for SQL expressiveness, it is at the same time much…