D squared F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation
Jiaoyang Li, Junhao Ruan, Shengwei Tang, Kaiyan Chang, Zhengtao Yu, Tong Xiao, Jingbo Zhu
cs.CL, cs.AI
Submitted: 2026-08-05
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large language models (LLMs) often generate inaccurate answers due to their reliance on static internal knowledge.
Terminology
Abstract
Large language models (LLMs) often generate inaccurate answers due to their reliance on static internal knowledge. Retrieval-augmented generation (RAG) addresses this limitation by integrating external knowledge and excelling at single-hop queries. However, it struggles with multi-hop questions that require cross-document reasoning. Existing methods, such as graph structured RAG or question decomposition, often lack dynamic decomposition and effective filtering, which leads to lower efficiency and accuracy. To overcome these limitations, we propose Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation (D2F-ReAG), a novel paradigm that adaptively controls reasoning depth by judging the reliability of the root-level reasoning. If the root reasoning is reliable, the model directly generates the answer. Otherwise, the question is logically decomposed into sub-questions, and the verified reasoning derived from these sub-questions is used to refine the root reasoning. Experiments on three multi-hop benchmarks demonstrate the effectiveness of our method in handling complex multi-hop questions.
Sources
- GPT-4 Technical Report
- You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
- The Llama 3 Herd of Models
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
- SUBQRAG: Sub-Question Driven Dynamic Graph RAG
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering