English(EN)SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation
新研究解决了文本到SQL的效率、正确性和漏洞问题
作者PulseAugur 编辑部·[10 个来源]·
研究人员正在开发新方法来提高文本到SQL系统的效率和可靠性。一种名为SQuaD-SQL的方法利用LLM引导的知识蒸馏，使小型语言模型能够以更低的计算成本在文本到SQL任务上实现高性能。另一项研究侧重于预测AI生成的SQL查询的正确性，发现LLM裁判和集成方法明显优于简单的信号，尽管泛化到未见过的模式仍然是一个挑战。此外，像Spider 2.0-AIFunc这样的新基准正在涌现，以评估AI原生的SQL能力，并且正在开发像SAGE这样的框架来自主发现文本到SQL模型中潜在的漏洞。
AI
arXiv:2607.08161v1 Announce Type: new Abstract: Text-to-SQL is a fundamental task in natural language processing that enables users to interact with structured databases using natural language. While large language models (LLMs) have demonstrated remarkable performance on this ta…
Text-to-SQL is a fundamental task in natural language processing that enables users to interact with structured databases using natural language. While large language models (LLMs) have demonstrated remarkable performance on this task, their substantial computational requirements…
arXiv:2607.06799v1 Announce Type: cross Abstract: Evaluating uncertainty in AI-generated SQL queries requires estimating whether a query is correct, where correct means it executes to the same result as a human-written reference. We study which signals predict correctness on hard…
arXiv:2607.06229v1 Announce Type: cross Abstract: Major cloud data platforms now expose large language model capabilities as native SQL functions, enabling analysts to perform classification, filtering, sentiment analysis, extraction, similarity search, and aggregation within ord…
Major cloud data platforms now expose large language model capabilities as native SQL functions, enabling analysts to perform classification, filtering, sentiment analysis, extraction, similarity search, and aggregation within ordinary SQL queries. Yet existing text-to-SQL benchm…
arXiv:2607.03833v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have achieved remarkable success in Text-to-SQL tasks, their deployment in real-world environments is hindered by latent reliability issues. Identifying these latent weaknesses is critical for bu…
arXiv cs.CL
TIER_1English(EN)·Yaron Anavi, Mor Aisenberg, Nadav Nesher, Elena Khabibullina, Isabella Cattinelli·
arXiv:2607.03991v1 Announce Type: cross Abstract: Repeated LLM calls are the standard way to estimate how trustworthy a Text-to-SQL result is: run the pipeline multiple times, judge each SQL execution, and use the consistency of the verdicts as a confidence signal. The open quest…
dev.to — LLM tag
TIER_1English(EN)·VINCENZO RAFAEL LLANOS NIÑO·
<p>Introduction</p> <p>Writing SQL queries is a fundamental skill for developers, data analysts, and database administrators. However, not everyone knows SQL syntax, and even experienced developers spend time writing repetitive queries.</p> <p>Recent advances in Generative AI and…
dev.to — LLM tag
TIER_1English(EN)·MARYMAR DANYTZA CALLOTICONA CHAMBILLA·
<h2> The problem with "classic" Text-to-SQL </h2> <p>The simplest way to connect an LLM to a database is a single-pass pipeline: the user writes a question in natural language, the model generates a SQL query, and that query is executed directly against the database. This is, for…
