QUASAR统一处理文本、表格和知识图谱，用小模型实现媲美大模型的问答效果。
RAG-based Question Answering over Heterogeneous Data and Text
- 基于RAG架构，分步骤检索证据并生成答案
- 在三个基准上表现优于或持平大模型，计算成本低得多
- 内置问题理解与证据重排，提升信息精准度
本文提出QUASAR系统，用于对非结构化文本、结构化表格和知识图谱进行统一的问答处理。该系统采用基于检索增强生成（RAG）的架构，包含证据检索与答案生成两个阶段，其中答案生成由中等规模语言模型驱动。此外，QUASAR还包含问题理解模块，以优化检索输入，并在将证据送入生成模块前进行重排序与过滤，确保最相关的信息被使用。在三个不同基准上的实验表明，该方法的问答质量达到或超过大型GPT模型水平，同时计算开销和能耗降低一个数量级以上。
原文摘要 · Abstract (English)
This article presents the QUASAR system for question answering over unstructured text, structured tables, and knowledge graphs, with unified treatment of all sources. The system adopts a RAG-based architecture, with a pipeline of evidence retrieval followed by answer generation, with the latter powered by a moderate-sized language model. Additionally and uniquely, QUASAR has components for question understanding, to derive crisper input for evidence retrieval, and for re-ranking and filtering the retrieved evidence before feeding the most informative pieces into the answer generation. Experiments with three different benchmarks demonstrate the high answering quality of our approach, being on par with or better than large GPT models, while keeping the computational cost and energy consumption orders of magnitude lower.
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。