相关论文: AI-Assisted SQL Authoring at Industry Scale

Despite strong performance on Text-to-SQL benchmarks, it remains unclear whether LLM-generated SQL programs are structurally reliable. In this work, we investigate the structural behavior of LLM-generated SQL queries and introduce…

There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding. Existing studies primarily focus on prompting powerful, closed-source models to generate seed training data followed by…

With advances in large language models (LLMs), researchers are creating new systems that can perform AI-driven analytics over large unstructured datasets. Recent work has explored executing such analytics queries using semantic operators --…

In the domain of semantic parsing, significant progress has been achieved in Text-to-SQL and question-answering tasks, both of which focus on extracting information from data sources in their native formats. However, the inherent…

"PL/SQL functions are slow," is common developer wisdom that derives from the tension between set-oriented SQL evaluation and statement-by-statement PL/SQL interpretation. We pursue the radical approach of compiling PL/SQL away, turning…

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…

Ensuring that Large Language Models (LLMs) generate text representative of diverse sub-populations is essential, particularly when key concepts related to under-represented groups are scarce in the training data. We address this challenge…

Automated analysis for engineering structures offers considerable potential for boosting efficiency by minimizing repetitive tasks. Although AI-driven methods are increasingly common, no systematic framework yet leverages Large Language…

Table understanding requires structured, multi-step reasoning. Large Language Models (LLMs) struggle with it due to the structural complexity of tabular data. Recently, multi-agent frameworks for SQL generation have shown promise in…

Existing refinement methods in LLM-based Text-to-SQL systems exhibit limited effectiveness. They often introduce new errors during the self-correction process and fail to detect and correct semantic inaccuracies. To address these gaps, we…

Rule-based reasoning over natural language input arises in domains where decisions must be auditable and justifiable: clinical protocols specify eligibility criteria in prose, evidence rules define admissibility through textual conditions,…

We present GraPPa, an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data. We construct synthetic question-SQL pairs over…

Large Language Models (LLMs) have demonstrated remarkable progress in translating natural language to SQL, but a significant semantic gap persists between their general knowledge and domain-specific semantics of databases. Historical…

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…

Text-to-SQL datasets are essential for training and evaluating text-to-SQL models, but existing datasets often suffer from limited coverage and fail to capture the diversity of real-world applications. To address this, we propose a novel…

Large Language Models (LLMs) have advanced recommendation capabilities through enhanced reasoning, but pose significant challenges for real-world deployment due to high inference costs. Conversely, while Small Language Models (SLMs) offer…

The SQL-based exploratory data analysis has garnered significant attention within the data analysis community. The emergence of large language models (LLMs) has facilitated the paradigm shift from manual to automated data exploration.…

Aim. There are 10s of thousands of code review comments each week at Meta. We developed Metamate for Code Review (MetaMateCR) that provides AI-assisted fixes for reviewer comments in production at scale. Method. We developed an internal…

Resolution of complex SQL issues persists as a significant bottleneck in real-world database applications. Current Large Language Models (LLMs), while adept at text-to-SQL translation, have not been rigorously evaluated on the more…

There is growing consensus that language model (LM) developers should not be the sole deciders of LM behavior, creating a need for methods that enable the broader public to collectively shape the behavior of LM systems that affect them. To…