English(EN) PEARL: Front-Loading Relational Chains for Multi-Hop Table Retrieval

PEARL框架增强了LLM的多跳表检索能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-31 05:56

研究人员推出了一种新颖的框架PEARL，旨在改进大型语言模型的多跳表检索能力。与之前对整个表进行编码的方法不同，PEARL通过垂直划分子表并离线生成多跳查询，采用了一种无需训练的方法。该方法将相关列编码为垂直划分的单元，能够在无需查询时LLM推理的情况下，有效地跨多个表进行检索。实验表明，PEARL的性能显著优于现有技术，在3跳查询上的R@2提升高达30.05%。 AI

影响提升了LLM在结构化数据检索和推理方面的能力。

排序理由详细介绍一种新的表检索方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍一种新的表检索方法的论文。[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: 10 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]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Susik Yoon · 2026-08-31 05:56

PEARL：用于多跳表格检索的前置关系链

While large language models (LLMs) have shown strong capabilities in tabular reasoning, retrieving relevant tables remains challenging due to the fragmented and relational structure of real-world data. Existing work typically relies on whole table representations that overlook cr…

本文如何被排名

报道来源 [1]

PEARL：用于多跳表格检索的前置关系链

相关实体

相关话题