Related papers: PIQL: Success-Tolerant Query Processing in the Clo…
Many interesting data sets available on the Internet are of a medium size---too big to fit into a personal computer's memory, but not so large that they won't fit comfortably on its hard disk. In the coming years, data sets of this…
In-context learning using large language models has recently shown surprising results for semantic parsing tasks such as Text-to-SQL translation. Prompting GPT-3 or Codex using several examples of question-SQL pairs can produce excellent…
Deterministic database systems have received increasing attention from the database research community in recent years. Despite their current limitations, recent proposals of distributed deterministic transaction processing systems…
Tabular data synthesis aims to generate high-quality data while preserving privacy. However, we find that existing tabular generative models exhibit a clear tradeoff in the small-data regime: improving data quality typically comes at the…
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…
Finding errors in machine learning applications requires a thorough exploration of their behavior over data. Existing approaches used by practitioners are often ad-hoc and lack the abstractions needed to scale this process. We present…
Modern data warehouses extend SQL with semantic operators that invoke large language models on each qualifying row, but the per-row inference cost is prohibitive at scale. Model cascades reduce this cost by routing most rows through a fast…
Probabilistic independence is a useful concept for describing the result of random sampling---a basic operation in all probabilistic languages---and for reasoning about groups of random variables. Nevertheless, existing verification methods…
We present an approach for dynamic information flow control across the application and database. Our approach reduces the amount of policy code required, yields formal guarantees across the application and database, works with existing…
Considerable concerns exist over privacy on social networks, and huge debates persist about how to extend the artifacts users need to effectively protect their rights to privacy. While many interesting ideas have been proposed, no single…
Text-to-SQL, the process of translating natural language into Structured Query Language (SQL), represents a transformative application of large language models (LLMs), potentially revolutionizing how humans interact with data. This paper…
Computer-based information technologies have been extensively used to help many organizations, private companies, and academic and education institutions manage their processes and information systems hereby become their nervous centre. The…
In the burgeoning era of big data, selecting the optimal database solution has become a critical decision for organizations across every industry. Big data demands a powerful database solution. Traditionally, SQL Database, Database ruled,…
As the use of technology increases and data analysis becomes integral in many businesses, the ability to quickly access and interpret data has become more important than ever. Information retrieval technologies are being utilized by…
It is now cost-effective to outsource large dataset and perform query over the cloud. However, in this scenario, there exist serious security and privacy issues that sensitive information contained in the dataset can be leaked. The most…
As large language models (LLMs) demonstrate increasingly powerful reasoning and orchestration capabilities, LLM-based agents are rapidly proliferating for complex data-related tasks. Despite this progress, the current design of how LLMs…
Much like on-premises systems, the natural choice for running database analytics workloads in the cloud is to provision a cluster of nodes to run a database instance. However, analytics workloads are often bursty or low volume, leaving…
Previous work has demonstrated that categories are useful and expressive models for databases. In the present paper we build on that model, showing that certain queries and constraints correspond to lifting problems, as found in modern…
The conversion of natural language into SQL language for querying databases (Text-to-SQL) has broad application prospects and has attracted widespread attention. At present, the mainstream Text-to-SQL methods are mainly divided into…
As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…