PulseAugur
实时 05:39:06

新的检索系统通过目录元数据提高文本到SQL的准确性

研究人员开发了一种名为Schema-First Retrieval的新检索系统,旨在提高文本到SQL系统的准确性。该系统嵌入目录元数据而非原始仓库数据,索引五种类型的目录对象:表、列、指标、关系和查询历史。通过采用并行向量搜索、 lineage expansion、cross-encoder reranking、workload memory和访问控制门,该系统旨在在SQL生成前提供更相关的模式上下文。在CRUSH4SQL和BIRD等数据集上的评估表明,表召回率显著提高,SQL执行错误大幅减少。 AI

影响 这种方法可以显著提高数据分析自然语言界面的可靠性和可用性。

排序理由 该集群包含一篇详细介绍新颖技术方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的检索系统通过目录元数据提高文本到SQL的准确性

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍新颖技术方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
57 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Adarsh Agrawal, Shashank Indukuri ·

    Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics

    arXiv:2606.28387v1 Announce Type: cross Abstract: Enterprise text-to-SQL systems often fail before SQL is generated: the model receives the wrong schema context. Modern warehouses contain thousands of tables, abbreviated columns, informal metrics, hidden join conventions, and per…