Caching one-hop knowledge-graph neighborhoods with LRU or LFU prevents repeated graph queries in KGQA systems, giving up to 1.91x faster graph retrieval but only about 1.06x end-to-end speedup.
Knowledge graph retrieval-augmented generation via gnn-guided prompting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
KGCache: Amortized Subgraph Retrieval for KG Reasoning with LLMs
Caching one-hop knowledge-graph neighborhoods with LRU or LFU prevents repeated graph queries in KGQA systems, giving up to 1.91x faster graph retrieval but only about 1.06x end-to-end speedup.