English(EN) Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL

新方法应对LLM Text-to-SQL的可靠性和收敛性

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-07 04:00

研究人员开发了新方法来解决由大型语言模型（LLM）驱动的Text-to-SQL系统的可靠性问题。一种方法SAGE，使用自动引导探索来发现和记录LLM生成的SQL查询中潜在的失败模式，展示了当前模型显著的脆弱性，并显示出跨模型可迁移性的潜力。另一种方法侧重于预测何时停止用于评估SQL结果一致性的重复LLM调用，根据收敛轨迹调整停止点，以提高在各种基准测试上的效率和可靠性。 AI

影响这些方法旨在提高基于LLM的Text-to-SQL系统的可靠性和效率，这对于值得信赖的数据库接口至关重要。

排序理由两篇在arXiv上发表的研究论文，详细介绍了改进Text-to-SQL系统的新颖方法。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Hanqing Wang, Yongdong Chi, Jian Yang, Lei Yang, Jiehui Zhao, Yun Chen, Guanhua Chen · 2026-07-07 04:00

Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL

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_1 English(EN) · Yaron Anavi, Mor Aisenberg, Nadav Nesher, Elena Khabibullina, Isabella Cattinelli · 2026-07-07 04:00

Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL

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…

报道来源 [2]

Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL

Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL

相关实体

相关话题