PulseAugur
中
实时 13:02:55
English(EN) Replacing Training with Memory: Listwise Selection for Text-to-SQL

新的文本到SQL方法使用记忆，绕过微调

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了MaP-SQL，一种新颖的文本到SQL系统方法，无需微调列表选择器。MaP-SQL不将选择标准作为模型参数进行学习，而是利用可重用的结构化记忆来编码自然语言、SQL操作和预期输出之间的映射。该方法通过跨输入排列的聚合排名来缓解位置偏差，从而提高选择的准确性和效率，在BIRD-dev基准测试中优于先前最先进的方法。 AI

影响 这种无需微调的方法可以简化文本到SQL系统的开发和部署，使其更易于访问和高效。

排序理由 该集群描述了一篇详细介绍文本到SQL系统新方法的学术论文。

在 Hugging Face Daily Papers 阅读 →

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

新的文本到SQL方法使用记忆，绕过微调

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
Research
该集群描述了一篇详细介绍文本到SQL系统新方法的学术论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
75 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 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Yeonseok Jeong, Soyoung Yoon, Seongjun Lee, Seung-won Hwang ·

    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…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    用记忆取代训练：用于Text-to-SQL的列表式选择

    MaP-SQL improves listwise Text-to-SQL selection without fine-tuning by using structured memory retrieval and permutation-based ranking aggregation.

相关实体

相关话题