[论文] Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems
来源:arXiv AI 论文收录:2026/8/24
✦ AI 解读
该论文提出一种用于RAG系统的评估代理,通过NLI事实核查、五信号毒化检测及加权聚合,计算信任指数T=0.4F+0.35C+0.25(1-P),以识别知识中毒和错误信息。在TruthfulQA基准上,使用Llama 3.3 70B达到91%准确率和100%精确率,对指令注入的召回率为100%,有效弥补了RAG系统的安全-可靠性差距。
Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) outputs in external knowledge, but RAG systems usually trust whatever they retrieve, creating a Security-Reliability Gap: high semantic relevance does not guarantee factual truth. Adversaries exploit this through knowledge poisoning, inserting malicious documents to cause targeted misinformation. We propose an Evaluation Agent, middleware that combines Natural Language Inference (NLI) factual verification, a five-signal poison detector with relevance-weighted aggregation, and a Trust Index T = 0.4 F + 0.35 C + 0.25 (1 - P ) with a non-linear dampener for high-contamination contexts. On TruthfulQA with Llama 3.3 70B, the agent reaches 91% accuracy and 100% precision, with 100% recall on instruction injection, while in-p
相关推荐
Risk of transmission of amyloid β pathology via transfused blood products
✦ AI 摘要该研究探讨了通过输血传播淀粉样β病理的风险,发表于《柳叶刀》。研究可能涉及朊病毒样传播机制,对血液制品安全性和阿尔茨海默病预防有重要启示。内容来自顶级医学期刊,但属于医学领域,与AI从业者直接关联较低。
NanoGPT Speedrun Frontier
✦ AI 摘要Prime Intellect发布NanoGPT Speedrun Frontier,展示在单台GPU上以极低成本训练GPT-2级别模型的优化技术。文章详细介绍了训练速度提升的多种策略,包括数据加载、混合精度、内核优化等,并提供了可复现的代码。该研究对资源有限的AI开发者具有重要参考价值,引发社区广泛讨论。
[论文] TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems
✦ AI 摘要TurboBias 2.0 是一个面向生产环境的 ASR 系统上下文偏置框架,旨在解决流式推理、批量解码、用户特定上下文列表和低运行时开销等实际需求。它扩展了 GPU 加速的 TurboBias,引入不区分大小写的提升图和每流批量解码,使批次中的每个话语都能使用独立的上下文配置,从而实现个性化上下文处理,提升识别准确率并保持高效。