研究库 论文知识库

内容库 / 论文

arXiv:2610.08463 · RAG 检索增强

UNREAL: Unifying Retrieval and Long-Context with a Single Model

UNREAL: Unifying Retrieval and Long-Context with a Single Model

类型：arxiv
标识：2610.08463
链接：http://arxiv.org/abs/2610.08463v1
主分类：rag
形态：method
TLDR：Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-internal mechanism can select evidence across this range. We introduce UNifying REtrieval And Long-Context with a Single Model (UNREAL), a model-native evidence selection framework to span corpus retrieval and long-context inference. UNREAL encodes chunks and derives retrieval queries directly from the frozen LLM's internal representations. It adds fewer than 500K trainable parameters and leaves the ba
副分类：llm-infra
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-10-07-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

仓库 griver/Q-RAG

仓库 Yogeswaran-A/RESEARCH-PAPER-RECOMMENDATION-SYSTEM-USING-MACHINE-LEARNING

文档 Tom-on-flyP-2026-07-25

笔记 FRAUDSkill + HEAL 双论文轻量精读(2026-09-22)

笔记 Tom 文献雷达 · Agent/RAG/长上下文 · 2026-08-22 08:40 UTC

笔记 KVAE Tokenizers arXiv:2608.05798 · multimodal · 精读与批判 v2

arXiv

2610.08463

TLDR

Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-internal mechanism can select evidence across this range. We introduce UNifying REtrieval And Long-Context with a Single Model (UNREAL), a model-native evidence selection framework to span corpus retrieval and long-context inference. UNREAL encodes chunks and derives retrieval queries directly from the frozen LLM's internal representations. It adds fewer than 500K trainable parameters and leaves the ba

arXiv ↗ 中文全文