A Query-Driven Graph Retrieval Framework with Adaptive Pruning for Multi-Hop Question Answering
Electronics · 2026-03-18 · 15 (6) · 1263
DOI: 10.3390/electronics15061263 ↗At a glance
Journal article in Electronics, published online on 2026-03-18. Written by Hao Wang and 6 co-authors. Cited 2 times so far (Crossref); 28 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, Jiangsu Science and Technology Programme.
Abstract (original language)
Multi-hop question answering (MHQA) requires models to retrieve and reason over evidence distributed across multiple documents, which remains challenging for conventional retrieval-augmented generation (RAG) approaches. Although RAG improves factual grounding by incorporating external knowledge, flat retrieval strategies often struggle to maintain coherent reasoning chains when implicit dependencies among entities and documents are involved. This paper presents a query-driven dual-layer graph retrieval framework for MHQA. The framework operates on a unified heterogeneous graph integrating entities, relations, and supporting texts, and dynamically constructs candidate subgraphs through joint retrieval over entities and relations, complemented by lexical retrieval signals. Reasoning paths are refined by combining structural strength modeling with contrastive learning-based path scoring, and an adaptive pruning strategy is employed to regulate evidence scale according to query complexity and path score distributions. Experiments on HotpotQA and 2WikiMultihopQA show that the proposed framework achieves higher EM and F1 scores than existing RAG and graph-based retrieval methods, particularly in complex multi-hop scenarios. These results indicate the importance of structured and query-adaptive evidence organization for multi-hop reasoning.
Funding
- National Natural Science Foundation of China
- Jiangsu Science and Technology Programme
Cite
APA
Wang, H., Wang, T., Sun, Z., Li, H., Cao, Z., Feng, L., & Wang, D. (2026). A Query-Driven Graph Retrieval Framework with Adaptive Pruning for Multi-Hop Question Answering. Electronics, 15(6), 1263. https://doi.org/10.3390/electronics15061263
Vancouver
Wang H, Wang T, Sun Z, Li H, Cao Z, Feng L, et al. A Query-Driven Graph Retrieval Framework with Adaptive Pruning for Multi-Hop Question Answering. Electronics. 2026;15(6):1263. doi:10.3390/electronics15061263
BibTeX
@article{Wang2026,
author = {Wang, Hao and Wang, Tianyue and Sun, Zhongrui and Li, He and Cao, Zhengyang and Feng, Lihang and Wang, Dong},
title = {A Query-Driven Graph Retrieval Framework with Adaptive Pruning for Multi-Hop Question Answering},
journal = {Electronics},
year = {2026},
volume = {15},
number = {6},
pages = {1263},
doi = {10.3390/electronics15061263}
}
EUVIMED