DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers

Researchers introduced DeFT-RAG, a retrieval-augmented generation method that decomposes multi-hop questions into self-contained sub-questions whose answers can be reused, targeting the failure of standard RAG when facts must be chained across several documents through intermediate entities. The approach addresses multi-hop questions that require chaining facts spread across documents via intermediate entities the question does not name. The work is a research contribution to improving LLM question answering over large corpora.

Retrieval-augmented generation RAG lets a large language model LLM answer questions by retrieving relevant passages from a large corpus. However, RAG struggles with multi-hop questions, which require chaining facts spread across several documents through intermediate entities that the question n