Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge Graphs
- 类型:arxiv
- 标识:2608.25986
- 链接:http://arxiv.org/abs/2608.25986v1
- 主分类:rag
- 形态:method
- 被引:0
- 被引来源:Semantic Scholar + OpenAlex
- S2被引:0
- OpenAlex被引:0
- 影响力被引:0
- TLDR:A novel framework for constructing a Context-Enhanced MMKG (CEMMKG) is proposed, effective in leveraging contextual information to improve MMKG-based RAG performance and its effectiveness across different MMKG-based RAG methods demonstrates its broad applicability.
- OpenAlex ID:W7204452208
- OpenAlex DOI:10.48550/arxiv.2608.25986
- DOI:10.48550/arxiv.2608.25986
- DOI来源:OpenAlex
- 开放获取:green
- 开放获取链接:https://arxiv.org/pdf/2608.25986
- OpenAlex更新:2026-09-01
- 副分类:multimodal
- 待LLM分类:否
- 标题中文:多模态知识图谱上的多粒度上下文增强 RAG
- TLDR中文:本文提出一种构建 Context-Enhanced MMKG (CEMMKG) 的新框架,能够有效利用上下文信息提升基于 MMKG 的 RAG 性能,并在不同基于 MMKG 的 RAG 方法上的有效性验证了其广泛适用性。
- 来源文件:
- /inbox/tom/_candidates/2026-08-27-agent-rag-longcontext-candidates.json
- [S2 enrich]
- [OpenAlex backfill]