多适配器系统提升多任务检索增强生成问答性能
MARAGS: A Multi-Adapter System for Multi-Task Retrieval Augmented Generation Question Answering
- 采用多个适配器应对不同任务需求，统一使用交叉编码器排序
- 在任务1中获第二名，任务2中位列第三
- 适合需要多任务推理与高效检索的RAG应用开发者
本文提出多适配器检索增强生成系统（MARAGS），用于Meta举办的KDD CUP 2024综合检索增强生成（CRAG）竞赛。CRAG数据集包含三个子任务，涵盖多样化问题主题、类型、时序答案及不同热度实体。系统基于标准Web-RAG框架，利用处理后的网页内容为大模型提供上下文，并通过API获取补充信息。MARAGS采用多个适配器分别应对各任务需求，结合标准交叉编码器对候选段落进行相关性排序。系统在任务1中取得第二名，在任务2中获得第三名。
原文摘要 · Abstract (English)
In this paper we present a multi-adapter retrieval augmented generation system (MARAGS) for Meta's Comprehensive RAG (CRAG) competition for KDD CUP 2024. CRAG is a question answering dataset contains 3 different subtasks aimed at realistic question and answering RAG related tasks, with a diverse set of question topics, question types, time dynamic answers, and questions featuring entities of varying popularity. Our system follows a standard setup for web based RAG, which uses processed web pages to provide context for an LLM to produce generations, while also querying API endpoints for additional information. MARAGS also utilizes multiple different adapters to solve the various requirements for these tasks with a standard cross-encoder model for ranking candidate passages relevant for answering the question. Our system achieved 2nd place for Task 1 as well as 3rd place on Task 2.
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。