METIS：具有配置自适应的快速质量感知RAG系统
METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation
AI总结：
METIS是首个联合调度查询并自适应调整RAG配置的系统，在4个数据集上将生成延迟降低1.64-2.54倍且不牺牲质量。
摘要：
RAG（检索增强生成）允许大语言模型（LLMs）借助外部知识生成更优的响应，但使用更多外部知识往往在提升生成质量的同时牺牲响应延迟。先前的工作要么通过更好的RAG查询调度来降低响应延迟，要么致力于最大化质量（涉及调整RAG工作流），但它们在优化RAG响应的延迟与质量之间的权衡方面存在不足。本文提出METIS，这是首个联合调度查询并自适应调整每个查询的关键RAG配置（如检索文本块数量和合成方法）的RAG系统，以平衡质量优化与响应延迟降低。使用4个流行的RAG-QA数据集，我们表明与最先进的RAG优化方案相比，METIS在不牺牲生成质量的情况下将生成延迟降低了1.64-2.54倍。
英文摘要：
RAG (Retrieval Augmented Generation) allows LLMs (large language models) to generate better responses with external knowledge, but using more external knowledge often improves generation quality at the expense of response delay. Prior work either reduces the response delay (through better scheduling of RAG queries) or strives to maximize quality (which involves tuning the RAG workflow), but they fall short in optimizing the tradeoff between the delay and quality of RAG responses. This paper presents METIS, the first RAG system that jointly schedules queries and adapts the key RAG configurations of each query, such as the number of retrieved text chunks and synthesis methods, in order to balance quality optimization and response delay reduction. Using 4 popular RAG-QA datasets, we show that compared with the state-of-the-art RAG optimization schemes, METIS reduces the generation latency by $1.64-2.54\times$ without sacrificing generation quality.
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。
