通过生成上下文知识融合弥合RAG中的语义鸿沟
Bridging Semantic Gaps in RAG through Generated Context Knowledge Fusion
浏览论文内容
中文总结 AI 辅助
针对RAG中查询与检索上下文语义不匹配的问题，提出KASB框架，通过智能知识融合对齐语义空间，提升段落选择质量，并在三个开放域问答数据集上验证有效性。
中文摘要 AI 辅助
检索增强生成（RAG）已成为自然语言处理中的基础框架，无缝集成信息检索与大型语言模型的生成能力。然而，该过程从根本上受到一个关键挑战的制约：查询与检索上下文之间的语义空间不匹配。我们提出知识感知语义桥接（KASB），一种新颖的框架，通过智能知识融合实现查询与检索文档之间的语义空间对齐，从而提升段落选择质量。我们的方法利用生成式知识与基于检索的知识的互补优势，通过多阶段过程增强相关性和准确性。我们在三个流行的开放域问答数据集上评估KASB，以证明我们方法的有效性。
英文摘要
Retrieval-Augmented Generation has established itself as a fundamental framework in natural language processing, seamlessly integrating information retrieval with the generative capabilities of large language models. However, this process is fundamentally constrained by a critical challenge: semantic space mismatch between queries and retrieved contexts. We propose Knowledge-Aware Semantic Bridging (KASB), a novel framework that improves passage selection quality through semantic space alignment between queries and retrieved documents through intelligent knowledge fusion. Our approach leverages the complementary strengths of generative and retrieval-based knowledge through a multistage process that enhances both relevance and accuracy. We evaluate KASB on three popular open-domain Question Answering datasets to demonstrate the effectiveness of our approach.
发表机构
- Beijing Wanlian Zhilian Technology Corporation Limited（北京万联智联科技有限公司）
- Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
- Sunshine Digital Intelligence Tech Co., Ltd.（阳光数字智能科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。
