English(EN) SPARSEUP: Towards Better Recipes for Training Modern Learned Sparse Retrievers

SPARSEUP训练方法将稀疏检索模型推向新的基准高点

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 16:27

研究人员开发了SPARSEUP，一种用于学习稀疏检索模型的新训练方法，可提高其效率和有效性。该方法通过优化logit分布和引入每位置扇出控制来应对这些模型的训练挑战。此外，还采用词汇合并策略来删除冗余条目，从而实现更精简的编码器。当应用于LateOn骨干网络时，SPARSEUP在BEIR-13基准测试中，在1.5亿参数以下的稀疏编码器中取得了56.4的平均nDCG@10的最新成果。 AI

影响提高了稀疏检索模型的效率和有效性，可能增强搜索和信息检索系统。

排序理由关于学习稀疏检索模型新训练方法的学术论文。[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; 关于学习稀疏检索模型新训练方法的学术论文。[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, 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: 5 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) · Cosimo Rulli · 2026-11-06 16:27

SPARSEUP：为训练现代学习稀疏检索器提供更好的配方

Learned sparse embeddings are a powerful alternative to dense retrieval, yet they have fallen behind single-vector and late interaction models. One reason for their limited adoption is that they are notoriously difficult to train, generally requiring very tight conditions to conv…

本文如何被排名

报道来源 [1]

SPARSEUP：为训练现代学习稀疏检索器提供更好的配方

相关实体

相关话题