METIS通过动态调整检索配置，让大模型问答更快更准。
METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation
- 动态调度检索任务并优化每条查询的配置参数
- 延迟降低1.64至2.54倍，质量不下降
- 适合追求响应速度与准确率平衡的应用场景
RAG（检索增强生成）使大语言模型能结合外部知识生成更优回答，但引入更多知识常以增加响应延迟为代价。现有方法或侧重降低延迟（通过优化检索任务调度），或追求最高质量（通过调优RAG流程），却难以兼顾延迟与质量的权衡。本文提出METIS，首个同时调度检索请求并自适应调整每条查询关键配置（如检索文本块数量、合成方法）的RAG系统，以实现质量与延迟的协同优化。在4个主流RAG问答数据集上验证，相比当前最优方案，METIS将生成延迟降低1.64至2.54倍，且不牺牲生成质量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。