Typed-RAG：面向非事实性问答的类型感知多维度分解方法

Typed-RAG: Type-aware Multi-Aspect Decomposition for Non-Factoid Question Answering

March 20, 2025

作者: DongGeon Lee, Ahjeong Park, Hyeri Lee, Hyeonseo Nam, Yunho Maeng

cs.AI

摘要

非事实类问答（NFQA）因其开放性、意图多样性及多维度推理需求而面临重大挑战，这使得包括检索增强生成（RAG）在内的传统事实类问答方法显得力不从心。与事实类问题不同，非事实类问题（NFQs）缺乏明确答案，需综合来自不同来源、跨越多种推理维度的信息。为应对这些局限，我们提出了Typed-RAG，一种在RAG框架内基于类型识别的多维度分解方法，专为NFQA设计。Typed-RAG将NFQs分类为辩论、经验、比较等不同类型，并采用基于维度的分解策略来优化检索与生成过程。通过将多维度NFQs分解为单一维度的子查询并整合结果，Typed-RAG能够生成信息更丰富、上下文更相关的回答。为评估Typed-RAG，我们引入了Wiki-NFQA，一个涵盖多种NFQ类型的基准数据集。实验结果表明，Typed-RAG在性能上超越基线模型，凸显了类型识别分解在NFQA中有效检索与生成的重要性。我们的代码与数据集已公开于https://github.com/TeamNLP/Typed-RAG。

English

Non-factoid question-answering (NFQA) poses a significant challenge due to its open-ended nature, diverse intents, and the need for multi-aspect reasoning, which renders conventional factoid QA approaches, including retrieval-augmented generation (RAG), inadequate. Unlike factoid questions, non-factoid questions (NFQs) lack definitive answers and require synthesizing information from multiple sources across various reasoning dimensions. To address these limitations, we introduce Typed-RAG, a type-aware multi-aspect decomposition framework within the RAG paradigm for NFQA. Typed-RAG classifies NFQs into distinct types -- such as debate, experience, and comparison -- and applies aspect-based decomposition to refine retrieval and generation strategies. By decomposing multi-aspect NFQs into single-aspect sub-queries and aggregating the results, Typed-RAG generates more informative and contextually relevant responses. To evaluate Typed-RAG, we introduce Wiki-NFQA, a benchmark dataset covering diverse NFQ types. Experimental results demonstrate that Typed-RAG outperforms baselines, thereby highlighting the importance of type-aware decomposition for effective retrieval and generation in NFQA. Our code and dataset are available at https://github.com/TeamNLP/Typed-RAG{https://github.com/TeamNLP/Typed-RAG}.