Related papers: RingSQL: Generating Synthetic Data with Schema-Ind…

Modern computing systems, such as HDFS and Spark, produce vast quantities of logs that developers use for tasks like anomaly detection and error analysis. To simplify log analysis, template generation methods have been proposed to…

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 rapid advancement of large language models (LLMs) such as GPT-3, PaLM, and Llama has significantly transformed natural language processing, showcasing remarkable capabilities in understanding and generating language. However, a…

Recent In-Context Learning based methods have achieved remarkable success in Text-to-SQL task. However, there is still a large gap between the performance of these models and human performance on datasets with complex database schema and…

With the advancement of speech synthesis technology, users have higher expectations for the naturalness and expressiveness of synthesized speech. But previous research ignores the importance of prompt selection. This study proposes a…

Exploring the generalization of a text-to-SQL parser is essential for a system to automatically adapt the real-world databases. Previous works provided investigations focusing on lexical diversity, including the influence of the synonym and…

The success of Large Language Models (LLMs) is inherently linked to the availability of vast, diverse, and high-quality data for training and evaluation. However, the growth rate of high-quality data is significantly outpaced by the…

Having access to realistic workloads for a given database instance is extremely important to enable stress and vulnerability testing, as well as to optimize for cost and performance. Recent advances in learned cost models have shown that…

Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and source data, remain absent. We conduct extensive controlled…

Natural Language to SQL (NL2SQL) has seen significant advancements with large language models (LLMs). However, these models often depend on closed-source systems and high computational resources, posing challenges in data privacy 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…

Solving tabular math word problems (TMWPs) has become a critical role in evaluating the mathematical reasoning ability of large language models (LLMs), where large-scale TMWP samples are commonly required for LLM fine-tuning. Since the…

Despite the remarkable performance of large language models (LLMs) in text-to-SQL (SQL generation), correctly producing SQL queries remains challenging during initial generation. The SQL refinement task is subsequently introduced to correct…

Text-to-SQL (Text2SQL) aims to map natural language questions to executable SQL queries. Although large language models (LLMs) have driven significant progress, current approaches struggle with poor transferability to open-source LLMs,…

Text2SQL, the task of generating SQL queries from natural language text, is a critical challenge in data engineering. Recently, Large Language Models (LLMs) have demonstrated superior performance for this task due to their advanced…

Generative language models have shown significant potential in single-turn Text-to-SQL. However, their performance does not extend equivalently to multi-turn Text-to-SQL. This is primarily due to generative language models' inadequacy in…

Although multi-agent collaborative Large Language Models (LLMs) have achieved significant breakthroughs in the Text-to-SQL task, their performance is still constrained by various factors. These factors include the incompleteness of the…

Recent developments in large language models (LLMs) have shown promise in their ability to generate synthetic query-document pairs by prompting with as few as 8 demonstrations. This has enabled building better IR models, especially for…

Recently, large language models (LLMs) have significantly improved the performance of text-to-SQL systems. Nevertheless, many state-of-the-art (SOTA) approaches have overlooked the critical aspect of system robustness. Our experiments…

Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought have demonstrated remarkable capabilities in code generation and mathematical reasoning. However, their potential in multi-turn Text-to-SQL tasks remains…