RAGViz：诊断与可视化检索增强生成
RAGViz: Diagnose and Visualize Retrieval-Augmented Generation
AI总结：
提出RAGViz工具，可视化RAG中令牌对检索文档的关注度，支持文档增删对比，高效运行，开源可用。
摘要：
检索增强生成（RAG）将领域特定来源的知识整合到大型语言模型中，以锚定答案生成。当前的RAG系统缺乏对上下文文档及模型对这些文档关注度的可定制可视化。我们提出RAGViz，一种RAG诊断工具，可视化生成令牌在检索文档中的关注度。凭借内置用户界面、检索索引和大型语言模型（LLM）骨干，RAGViz提供两大主要功能：（1）令牌和文档级注意力可视化，及（2）上下文文档添加和移除时的生成对比。作为开源工具包，RAGViz可轻松托管自定义嵌入模型和HuggingFace支持的LLM骨干。利用混合ANN（近似最近邻）索引、内存高效的LLM推理工具和自定义上下文片段方法，RAGViz在中等GPU节点上以约5秒的中位查询时间高效运行。我们的代码可在https://github.com/cxcscmu/RAGViz获取。RAGViz的演示视频可在https://youtu.be/cTAbuTu6ur4观看。
英文摘要：
Retrieval-augmented generation (RAG) combines knowledge from domain-specific sources into large language models to ground answer generation. Current RAG systems lack customizable visibility on the context documents and the model's attentiveness towards such documents. We propose RAGViz, a RAG diagnosis tool that visualizes the attentiveness of the generated tokens in retrieved documents. With a built-in user interface, retrieval index, and Large Language Model (LLM) backbone, RAGViz provides two main functionalities: (1) token and document-level attention visualization, and (2) generation comparison upon context document addition and removal. As an open-source toolkit, RAGViz can be easily hosted with a custom embedding model and HuggingFace-supported LLM backbone. Using a hybrid ANN (Approximate Nearest Neighbor) index, memory-efficient LLM inference tool, and custom context snippet method, RAGViz operates efficiently with a median query time of about 5 seconds on a moderate GPU node. Our code is available at https://github.com/cxcscmu/RAGViz. A demo video of RAGViz can be found at https://youtu.be/cTAbuTu6ur4.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
