Skip to content
Open access

Path-Aware Evidence Stitching for Budgeted Dual-Index Retrieval: A Controlled Multi-Hop Study

Oct 2026 · International journal of information and communication technology trends · 0 citations · 28 references

TL;DR

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.

Abstract

Budgeted graph skeletons reduce expensive indexing but can disconnect relational evidence that remains available in a complementary lexical index. We investigate 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. A workload-weighted selector combines historical query-path counts with edge betweenness; controlled baselines instantiate kNN eigenvector skeleton selection, weighted term–chunk postings, Personalized PageRank, and reciprocal rank fusion. After exploratory development, we freeze the parameters and execute a disjoint evaluation on three fully synthetic stochastic-block corpora containing 1,849 relation records and 480 queries. At 20% skeleton allocation, 100 lexical candidates and top-eight output, route stitching increases strict reference-path coverage of a betweenness skeleton from 13.96% to 57.50%. Workload weighting obtains 59.17% against an otherwise identical betweenness-stitch baseline, a 1.67-point difference with a paired 95% bootstrap interval of −0.63 to 4.17 points. Both stitched variants support some valid shortest route on approximately 98% of queries, and removing PageRank does not lower strict coverage. The findings isolate useful cross-index retrieval behavior under clean synthetic entity metadata; effects on natural-language QA and generation remain to be established.

Read PDF

Similar papers

Open access Oct 2026

Authority-Aware GraphRAG for Explainable Tax-Risk Evidence Retrieval: A Controlled Evaluation of Typed Legal Graph Expansion

Tax-risk analysis needs evidence sets that include a governing provision, companion rules, and a visible relationship path, rather than a single high-scoring passage. We study the retrieval stage of graph-grounded tax analysis through an executable, controlled benchmark. Building on citation-graph expansion used in tax...

Thomas Gupta, A. Henderson · 0 citations
Open access 2026

Interaction-Budget-Matched Analysis of Compact Cross-Encoder Reranking in Hybrid Retrieval

Hybrid retrieval pipelines combine lexical retrieval, semantic selection, and cross-encoder reranking, but apparent gains can be confounded when systems receive different numbers of expensive query–document interactions. This study presents an interaction-budget-matched empirical analysis across eight BEIR collections,...

Ibrahim Mohd Jamadi, S. Anuar, S. M. Ijad et al. · 0 citations

Corpus-Guided Dual-Path Propagation for Graph Retrieval-Augmented Generation

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...

Ba-Xian Liu, Tong Wei · 0 citations
Book Open access Nov 2026

KG-ARMM: Residual Structural Fusion for Graph-Augmented Personalized Retrieval

Dense multimodal retrieval scales well, but it can miss relational evidence from user histories, item neighborhoods, and domain entities. We present KG-ARMM, a retrieval-compatible Residual Structural Fusion (RSF) framework. A text-and-poster backbone supports approximate nearest-neighbor (ANN) candidate generation; an...

Mohamed Elrfaey, T. Gulliver · 0 citations
#artificial intelligence Preprint Open access Oct 2026

Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM

GraphRAG pipelines construct auxiliary structures during offline indexing--semantic summaries, hierarchical edges, and pre-computed scores--that determine how retrieval is prioritised at query time. Prior attacks target only instance-level components (nodes, edges, triples), overlooking these schema-level structures. W...

Ji-sun Park, John Le, Heath Cooper · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.