MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG

• URL: http://arxiv.org/abs/2608.02195v1
• Date: Mon, 03 Aug 2026 13:17:49 GMT
• Title: MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG
• Abstract summary: Multi-hop question answering is a fundamental challenge in retrieval-augmented generation.<n>MeGRAG represents multi-hop reasoning as a path-structured multi-granular evidence graph.<n>MeGRAG uses the resulting intermediate answer and prior reasoning to decide whether the Initial Query has been resolved.
• Score: 13.995448370079728
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-hop question answering is a fundamental challenge in retrieval-augmented generation (RAG), because deriving an answer requires integrating dispersed evidence. Iterative RAG (iRAG) is widely used for this challenge, but existing methods have two limitations. First, most methods still support each reasoning step with single-granularity evidence, making it difficult to balance information density and contextual noise. Second, existing methods often answer the original question only after aggregating evidence retrieved across intermediate steps, so redundant evidence and intermediate retrieval errors may accumulate and degrade the final answer. To address these limitations, we propose MEGRAG, an answer-aware framework that represents multi-hop reasoning as a path-structured multi-granular evidence graph. Offline, MEGRAG links passages to their sentences and extracted triples through a cross-granularity index. Online, it retrieves passages for the current query and selects aligned evidence, starting with compact triples and adding sentence or passage context as needed. MEGRAG uses the resulting intermediate answer and prior reasoning to decide whether the Initial Query has been resolved. If not, it identifies the missing information and formulates a focused next query; otherwise, it stops retrieval and returns the answer. Extensive experiments demonstrate consistent gains over a diverse set of RAG baselines.

Related papers

• Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval [19.37201042661162]
  We propose a training-free multi-hop retrieval framework that integrates evidence-conditioned exploration, passage-specific contrastive refinement, and coverage-aware final ranking.<n> Experiments on MuSiQue, HotpotQA, and 2WikiMultihopQA demonstrate consistent improvements in retrieval quality and downstream QA performance over baselines.
  arXiv  Detail & Related papers  (2026-09-07T05:13:56Z)
• Hierarchical Evidence-Driven Reasoning for Long Document Understanding [95.51688464037096]
  We introduce HIEVI-RAG, a hierarchical, evidence-driven multimodal RAG framework for closed-domain document understanding.<n>Our framework significantly outperforms existing open-source baselines and exceeds the strongest reported baseline by an average of 8.05% in accuracy.
  arXiv  Detail & Related papers  (2026-07-06T03:08:28Z)
• BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence [19.79339768762567]
  We introduce BRIDGE, a benchmark for multi-hop reasoning over long scientific papers.<n>The dataset supports both chain-like and fan-out structures and provides explicit multi-hop reasoning annotations.
  arXiv  Detail & Related papers  (2026-03-09T03:54:08Z)
• SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering [24.405588261303834]
  SentGraph is a sentence-level graph-based RAG framework that explicitly models fine-grained logical relationships between sentences for multi-hop question answering.<n>During online retrieval, SentGraph performs graph-guided evidence selection and path expansion to retrieve fine-grained sentence-level evidence.
  arXiv  Detail & Related papers  (2026-01-06T13:39:51Z)
• SUBQRAG: Sub-Question Driven Dynamic Graph RAG [34.20328335590984]
  SubQRAG is a sub-question-driven framework that enhances reasoning depth.<n>SubQRAG decomposes a complex question into an ordered chain of verifiable sub-questions.<n> Experiments on three multi-hop QA benchmarks demonstrate that SubQRAG achieves consistent and significant improvements.
  arXiv  Detail & Related papers  (2025-10-09T02:55:58Z)
• Question Decomposition for Retrieval-Augmented Generation [2.6409776648054764]
  We propose a RAG pipeline that incorporates question decomposition into sub-questions.<n>We show that question decomposition effectively assembles complementary documents, while reranking reduces noise.<n>Although reranking itself is standard, we show that pairing an off-the-shelf cross-encoder reranker with LLM-driven question decomposition bridges the retrieval gap on multi-hop questions.
  arXiv  Detail & Related papers  (2025-07-01T01:01:54Z)
• Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning [62.640169289390535]
  SPLIT-RAG is a multi-agent RAG framework that addresses the limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval.<n>The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG.<n>The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types.<n>A hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications.
  arXiv  Detail & Related papers  (2025-05-20T06:44:34Z)
• Multi-grained Evidence Inference for Multi-choice Reading Comprehension [62.0773160298008]
  Multi-choice Machine Reading (MRC) is a major and challenging task for machines to answer questions according to provided options. We propose a novel general-purpose model enhancement which integrates multi-grained evidence comprehensively, named Multi-grained evidence inferencer (Mugen) Mugen extracts three different granularities of evidence, and integrates evidence with the original passages, achieving significant and consistent performance improvement on four multi-choice MRC benchmarks.
  arXiv  Detail & Related papers  (2023-10-27T11:36:18Z)
• Answering Questions by Meta-Reasoning over Multiple Chains of Thought [53.55653437903948]
  We introduce Multi-Chain Reasoning (MCR), an approach which prompts large language models to meta-reason over multiple chains of thought. MCR examines different reasoning chains, mixes information between them and selects the most relevant facts in generating an explanation and predicting the answer.
  arXiv  Detail & Related papers  (2023-04-25T17:27:37Z)
• Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering [71.49131159045811]
  Multi-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions. We propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation.
  arXiv  Detail & Related papers  (2022-08-22T13:24:25Z)
• Modeling Multi-hop Question Answering as Single Sequence Prediction [88.72621430714985]
  We propose a simple generative approach (PathFid) that extends the task beyond just answer generation. PathFid explicitly models the reasoning process to resolve the answer for multi-hop questions. Our experiments demonstrate that PathFid leads to strong performance gains on two multi-hop QA datasets.
  arXiv  Detail & Related papers  (2022-05-18T21:57:59Z)
• Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering [40.58976291178477]
  We introduce a simple, fast, and unsupervised iterative evidence retrieval method. Despite its simplicity, our approach outperforms all the previous methods on the evidence selection task. When these evidence sentences are fed into a RoBERTa answer classification component, we achieve state-of-the-art QA performance.
  arXiv  Detail & Related papers  (2020-05-04T00:19:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.