研究人员开发了一种训练知识库的新方法，该知识库充当 AI 代理的策展文档库。该方法将知识库本身视为一个模型，使用带有问答对作为标签的监督学习来训练一个编辑和构建该库的代理。与无监督实体索引相比，该系统在准确性和操作节省方面表现出显著的改进，操作节省提高了 1.6 倍，准确性提高了 1.8 倍。发现这些改进的泛化能力取决于训练数据中问答键的覆盖范围。 AI
影响 这项研究通过改进 AI 代理访问和利用策展知识库信息的方式，有望带来更高效、更准确的 AI 代理。
排序理由 该集群包含一篇详细介绍 AI 系统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 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2608.21829v1 Announce Type: cross Abstract: Retrieval-augmented generation treats the document store as a frozen input, and the systems that instead let an agent curate one never measure what curation does to the store. We invert the framing: the knowledge base is the model…
Retrieval-augmented generation treats the document store as a frozen input, and the systems that instead let an agent curate one never measure what curation does to the store. We invert the framing: the knowledge base is the model. A training agent answers a supervised question a…
Retrieval-augmented generation treats the document store as a frozen input, and the offline pipelines that do build structure over it build it unsupervised -- a whole corpus indexed at uniform effort, with no signal about which structure a question will need. We instead treat the…