新的PDMR框架通过多ID方法增强文档检索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-08 13:58

研究人员推出了一种新的生成式检索框架——Passage-Driven Multi-ID Retrieval (PDMR)，该框架通过为每个文档分配多个段落级标识符来增强文档检索能力。这种方法允许模型将查询与文档的特定语义方面进行匹配，克服了可能导致信息丢失的单一标识符系统的局限性。PDMR在NQ320K和MS MARCO Document等基准数据集上展示了改进的性能，在召回率和平均倒数排名方面优于现有的生成式和非生成式方法。 AI

影响这种新的检索方法可以通过更好地处理多方面文档来提高搜索系统的准确性和鲁棒性。

排序理由该集群包含一篇详细介绍信息检索新方法的论文。[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; 该集群包含一篇详细介绍信息检索新方法的论文。[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, other; 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: 29 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 Română(RO) · Mohand Boughanem · 2026-09-08 13:58

PDMR：驱动文档检索的多通道ID

Generative Retrieval (GR) models map queries directly to document identifiers, replacing conventional retrieval over external sparse or dense indexes with autoregressive identifier generation. However, most generative retrieval frameworks rely on a single-identifier assumption, m…

本文如何被排名

报道来源 [1]

PDMR：驱动文档检索的多通道ID

相关实体

相关话题