让大模型不仅找知识，还能按任务需求合理使用。
RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
- 构建知识与应用示例双语料库，检索时同步获取
- 在数学、法律、医疗领域平均提升3-5%，最高达13.5%
- 适合需要精准知识应用的高阶任务场景
通过检索增强生成（RAG）整合外部知识，已成为提升大语言模型在知识密集型任务中表现的基础方法。然而，现有RAG范式常忽视知识的应用环节，导致检索到的事实与任务推理之间存在断层。本文提出RAG+，一种原则性且模块化的扩展框架，将应用感知推理显式融入RAG流程。RAG+构建由知识和对齐应用示例组成的双重语料库，可在推理阶段联合检索。该设计使大语言模型不仅能获取相关信息，还能在结构化、目标导向的推理过程中加以应用。在多个模型上针对数学、法律和医疗领域的实验表明，RAG+持续优于标准RAG变体，平均性能提升3-5%，复杂场景下最高达13.5%。通过弥合检索与可操作应用之间的鸿沟，RAG+推动了更符合认知逻辑的知识融合框架，助力实现更可解释、更强能力的大语言模型。
原文摘要 · Abstract (English)
The integration of external knowledge through Retrieval-Augmented Generation (RAG) has become foundational in enhancing large language models (LLMs) for knowledge-intensive tasks. However, existing RAG paradigms often overlook the cognitive step of applying knowledge, leaving a gap between retrieved facts and task-specific reasoning. In this work, we introduce RAG+, a principled and modular extension that explicitly incorporates application-aware reasoning into the RAG pipeline. RAG+ constructs a dual corpus consisting of knowledge and aligned application examples, created either manually or automatically, and retrieves both jointly during inference. This design enables LLMs not only to access relevant information but also to apply it within structured, goal-oriented reasoning processes. Experiments across mathematical, legal, and medical domains, conducted on multiple models, demonstrate that RAG+ consistently outperforms standard RAG variants, achieving average improvements of 3-5%, and peak gains up to 13.5% in complex scenarios. By bridging retrieval with actionable application, RAG+ advances a more cognitively grounded framework for knowledge integration, representing a step toward more interpretable and capable LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。