English(EN) Replacing Training with Memory: Listwise Selection for Text-to-SQL

新的Text-to-SQL方法用记忆取代训练

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-02 04:00

研究人员开发了一种新颖的、无需微调的Text-to-SQL系统方法，该方法用结构化记忆方法取代了传统训练。这种名为MaP-SQL的新技术利用从训练数据中提取的可重用记忆来编码自然语言、SQL操作和预期输出之间的映射。通过聚合多个输入排列的排名并减轻排序偏差，MaP-SQL提高了选择的准确性和效率，在BIRD-dev等基准测试中表现优于先前最先进的方法。 AI

影响这种无需微调的方法可以降低开发先进Text-to-SQL系统的计算成本。

排序理由这是一篇详细介绍Text-to-SQL系统新方法的学术论文。[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 →

本文如何被排名

Signal score: 29 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍Text-to-SQL系统新方法的学术论文。[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, model release; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yeonseok Jeong, Soyoung Yoon, Seongjun Lee, Seung-won Hwang · 2026-09-02 04:00

用记忆取代训练：用于Text-to-SQL的列表式选择

arXiv:2609.00834v1 Announce Type: cross Abstract: Modern Text-to-SQL systems often follow generate-execute-select pipelines, generating multiple candidate queries then selecting the best one. Listwise selection, by jointly comparing multiple candidates, has been widely adopted, b…

本文如何被排名

报道来源 [1]

用记忆取代训练：用于Text-to-SQL的列表式选择

相关实体

相关话题