Typed-RAG：面向非事實性問答的類型感知多維度分解

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

非事實性問答（NFQA）因其開放性、多樣化的意圖以及需要多維度推理而面臨重大挑戰，這使得包括檢索增強生成（RAG）在內的傳統事實性問答方法顯得不足。與事實性問題不同，非事實性問題（NFQs）缺乏明確答案，需要從多個來源綜合信息，涵蓋不同的推理維度。為解決這些限制，我們在RAG範式中引入了Typed-RAG，這是一個類型感知的多維度分解框架，專門用於NFQA。Typed-RAG將NFQs分類為不同的類型——如辯論、經驗和比較——並應用基於維度的分解來優化檢索和生成策略。通過將多維度的NFQs分解為單一維度的子查詢並聚合結果，Typed-RAG生成更具信息量和上下文相關性的回答。為了評估Typed-RAG，我們引入了Wiki-NFQA，這是一個涵蓋多種NFQ類型的基準數據集。實驗結果表明，Typed-RAG優於基線方法，從而凸顯了類型感知分解在NFQA中有效檢索和生成的重要性。我們的代碼和數據集可在https://github.com/TeamNLP/Typed-RAG{https://github.com/TeamNLP/Typed-RAG}獲取。

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}.