将文档结构形式化为多模态超图(Multimodal Hypergraph),以超边作为统一语义容器来封装跨文本、图像和表格的多路关联,超越点对点建模,并引入 Anchor-driven Incremental Refinement 机制。This paper formalizes the document structure as a Multimodal Hypergraph, utilizing hyperedges as unified semantic containers to encapsulate multi-way associations across text, images, and tables, thereby transcending point-to-point modeling and introducing an Anchor-driven Incremental Refinement mechanism.
论文
111 张论文卡片 · RAG 检索增强 · 方法
Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement
基于超图的多模态检索增强生成与增量优化
DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption
DSPrompt:面向 M-RAG 投毒攻击的动态软提示防御
提出 DSPrompt,一种 Dynamic Soft Prompt 防御框架,无需修改检索 pipeline,直接重塑 retriever 的 embedding 语义,并以极低的计算成本 consistently 优于现有防御基线。DSPrompt is proposed, a Dynamic Soft Prompt defense framework that directly reshapes the retriever's embedding semantics, without modifying the retrieval pipeline, and is consistently outperforming existing defense baselines at a fraction of their computational cost.
When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation
当上下文误导时:面向鲁棒检索增强生成的意图引导解码
提出 Intent-Guided Decoding (IGD),一个根据用户意图在检索上下文和参数化记忆之间进行仲裁的框架,显著提升了 RAG 中的事实恢复能力。Intent-Guided Decoding (IGD) is proposed, a framework that arbitrates between retrieved context and parametric memory according to user intent and substantially improves factual recovery in RAG.