仅分数蒸馏创建紧凑型密集检索模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-13 12:18

研究人员开发了一种仅分数蒸馏方法来创建紧凑型密集检索模型。该技术允许一个较小的学生模型仅使用分数向量来学习大型教师模型的排名行为，而无需访问教师的内部状态。蒸馏后的模型可以弥合基础模型和教师模型之间性能差距的 50%，为查询和文档编码提供了显著的速度提升。 AI

影响通过创建更小、更快的检索模型版本，实现大型检索模型更高效的部署。

排序理由学术论文，详细介绍了信息检索中模型蒸馏的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

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; 学术论文，详细介绍了信息检索中模型蒸馏的新方法。[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: 79 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。

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Salem Lahlou · 2026-07-13 12:18

Score-Only Distillation for Compact Dense Retrieval

Large embedding models improve retrieval quality, but serving large encoders online is expensive. We study whether a compact retriever can learn teacher ranking behavior from score vectors without access to teacher hidden states. The student trains on rows built from ground-truth…