STITCH-RAG is proposed, a hypergraph-based framework with three coupled components that combines topic-space propagation with deterministic chunk-index linkage across name-equivalent states under frequency-adaptive decay and characterize the condition under which this prior assigns more PPR mass to ground-truth evidence than a binary prior.
Abstract
Multi-hop retrieval-augmented generation requires a retriever to connect evidence distributed across documents while preserving a concise, faithful generation context. Existing indexes leave two complementary gaps: chunk-based RAG can break cross-passage evidence chains, whereas an unlabeled pairwise projection without generating-topic provenance cannot jointly preserve topic-level co-participation and per-occurrence entity descriptions. We propose STITCH-RAG, a hypergraph-based framework with three coupled components. First, a semi-merged topic hypergraph encodes multi-entity co-participation as topic-summary hyperedges while retaining per-chunk entity states linked by canonical-name equivalence. Second, spatio-temporal influence bridging propagation (STIBP) combines topic-space propagation with deterministic chunk-index linkage across name-equivalent states under frequency-adaptive decay. Third, continuous STIBP scores replace binary entity-match seeds in localized Personalized PageRank (PPR). We characterize the condition under which this prior assigns more PPR mass to ground-truth evidence than a binary prior. Under the reported protocol, STITCH-RAG attains the highest reported Contain-Acc and LLM-Acc point estimates among the compared methods on HotpotQA and 2WikiMultiHopQA, and higher Recall@8 than the methods included in the standardized retrieval comparison. Results on the mixed-domain benchmark remain auxiliary preference-based evidence because only LLM-judged accuracy is available.
Dual-Hypergraph Indexing (DHI), a hierarchical representation framework that elevates discrete facts into structured analytical insights, provides a robust architecture for next-generation multi-hop RAG.
Qi Sun, Xing-Liang Hou, Cai-Bo Li et al.· arXiv.org· 1 citation
Graph-based retrieval-augmented generation supports multi-hop retrieval by organizing corpus information into graphs. However, existing relation-free graph retrieval methods rely primarily on query-sentence similarity to search for evidence. This can exclude useful bridging evidence with low query similarity and activa...
Graph-based retrieval-augmented generation (GraphRAG) answers multi-hop questions by organizing a corpus into a graph and retrieving along its structure. Existing retrieval methods face two limitations. Diffusion- and similarity-based methods expand retrieval along fixed edge weights or by similarity to the question, w...
Jia-Te Liu, Liu-Yi Chen, Xiao-Fei Yuan et al.· 0 citations
Retrieval-augmented generation (RAG) systems ground large language models (LLMs) by retrieving external evidence and conditioning generation on the retrieved context. Although dense retrieval is effective for local semantic matching, independently ranked retrieval can return redundant passages, miss cross-chunk depende...
Z. Sahinoglu, A. Mohammed, Buse Yaren Kazangirler et al.· 0 citations
A query-time stitching mechanism that temporarily joins selected graph edges with the highest-ranked lexical candidates and prioritizes a coherent shortest route within the final evidence budget is investigated, isolate useful cross-index retrieval behavior under clean synthetic entity metadata.
Seojun Davis, Julian Tran· International journal of inf...· 0 citations
Multi-hop retrieval-augmented generation (RAG) requires finding documents whose evidence is useful in combination. Query relevance and graph connectivity help locate related content, but neither directly measures the additional information one document contributes given another. We introduce SG$^2$RAG, a framework that...
Ze-Liang Li, Xiao-Fen Xing, K. Guo et al.· 0 citations