A citation-graph retrieval framework that entangles sparse and dense relevance signals in a GNN over paper chunks reports state-of-the-art Hit@1 and answer accuracy on two research QA benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs
A citation-graph retrieval framework that entangles sparse and dense relevance signals in a GNN over paper chunks reports state-of-the-art Hit@1 and answer accuracy on two research QA benchmarks.