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.