{"slug": "deft-rag-decomposing-multi-hop-questions-into-self-contained-sub-questions-with", "title": "DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers", "summary": "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.", "body_md": "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", "url": "https://wpnews.pro/news/deft-rag-decomposing-multi-hop-questions-into-self-contained-sub-questions-with", "canonical_source": "https://aiflash.com/news/144508/", "published_at": "2026-11-03 03:00:31+00:00", "updated_at": "2026-11-03 03:20:07.883033+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "natural-language-processing", "ai-research", "generative-ai"], "entities": ["DeFT-RAG"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/deft-rag-decomposing-multi-hop-questions-into-self-contained-sub-questions-with", "markdown": "https://wpnews.pro/news/deft-rag-decomposing-multi-hop-questions-into-self-contained-sub-questions-with.md", "text": "https://wpnews.pro/news/deft-rag-decomposing-multi-hop-questions-into-self-contained-sub-questions-with.txt", "jsonld": "https://wpnews.pro/news/deft-rag-decomposing-multi-hop-questions-into-self-contained-sub-questions-with.jsonld"}}