通过识别问题类型并拆解多角度问题，提升非事实类问答的生成质量。
Typed-RAG: Type-Aware Decomposition of Non-Factoid Questions for Retrieval-Augmented Generation
- 按问题类型拆解非事实类问题，每部分聚焦单一维度。
- 在多个类型上显著优于现有RAG与大模型方法，提升回答相关性。
- 适合需要深入分析、多角度推理的开放问答场景。
非事实类问答（NFQA）因开放式特征、用户意图多样及多维度推理需求，仍具挑战性，传统检索增强生成（RAG）方法表现受限。为此，我们提出Typed-RAG框架，实现对非事实类问题的类型感知分解。首先将问题分类为预定义类型（如辩论、经历、对比），然后将其拆分为聚焦特定方面的子问题。该分解策略提升了检索相关性与答案质量。通过整合各子问题结果，生成更丰富且语境契合的回答。此外，我们构建了Wiki-NFQA基准数据集，涵盖多种非事实类问题类型。实验表明，Typed-RAG在多个指标上持续优于基于LLM或RAG的现有方法，验证了类型感知分解在提升检索与生成效果上的有效性。代码与数据集已开源。
原文摘要 · Abstract (English)
Addressing non-factoid question answering (NFQA) remains challenging due to its open-ended nature, diverse user intents, and need for multi-aspect reasoning. These characteristics often reveal the limitations of conventional retrieval-augmented generation (RAG) approaches. To overcome these challenges, we propose Typed-RAG, a framework for type-aware decomposition of non-factoid questions (NFQs) within the RAG paradigm. Specifically, Typed-RAG first classifies an NFQ into a predefined type (e.g., Debate, Experience, Comparison). It then decomposes the question into focused sub-queries, each focusing on a single aspect. This decomposition enhances both retrieval relevance and answer quality. By combining the results of these sub-queries, Typed-RAG produces more informative and contextually aligned responses. Additionally, we construct Wiki-NFQA, a benchmark dataset for NFQA covering a wide range of NFQ types. Experiments show that Typed-RAG consistently outperforms existing QA approaches based on LLMs or RAG methods, validating the effectiveness of type-aware decomposition for improving both retrieval quality and answer generation in NFQA. Our code and dataset are available on https://github.com/TeamNLP/Typed-RAG.
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。