English(EN) Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation

新的策略内训练方法改进了复杂问题的多跳检索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-31 04:00

研究人员开发了一种新的策略内训练方法，用于多跳检索增强生成中使用的嵌入模型。该方法在模型自身可能错误的检索上进行训练，旨在提高其为复杂问题找到所有必要证据的能力。该方法在 HotpotQA 和 2WikiMultiHopQA 数据集的挑战性变体上表现出改进的性能，证明了从自身错误中恢复的更强能力。 AI

影响提高了复杂、多文档问题的检索准确性，可能改进 RAG 系统的性能。

排序理由详细介绍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.AI 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, 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: 3 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.AI TIER_1 English(EN) · Chenjie Qiu, Zixuan Zeng, Shaobin Shi, Bingfeng Chen, Dongsheng Luo, Boyan Xu · 2026-10-31 04:00

从自身错误中检索：用于多跳检索增强生成的策略内嵌模型训练

arXiv:2610.40409v1 Announce Type: new Abstract: Complex questions in retrieval-augmented generation require evidence spread over several documents, and an answer is reliable only when the retriever finds all of it. Chain embedding retrievers collect such evidence step by step, re…

本文如何被排名

报道来源 [1]

从自身错误中检索：用于多跳检索增强生成的策略内嵌模型训练

相关实体

相关话题