Typed-RAG: Type-aware Multi-Aspect Decomposition for Non-Factoid Question Answering
DongGeon Lee, Ahjeong Park, Hyeri Lee, Hyeonseo Nam, Yunho Maeng
2025-03-25
Summary
This paper is about improving how AI answers complex, open-ended questions that don't have one simple answer.
What's the problem?
AI struggles to answer complex questions that require pulling information from multiple sources and considering different angles.
What's the solution?
The researchers created a new AI system called Typed-RAG that identifies the type of question being asked (like a debate or comparison) and then breaks it down into smaller parts to find the best information and generate a comprehensive answer.
Why it matters?
This work matters because it can lead to AI that is better at answering complex questions, which is useful for research, customer service, and many other applications.
Abstract
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}.