CKG-LLMA augments knowledge graphs with LLM advice and uses learned triplet confidence and dual-view contrastive learning to improve KG-based recommendation accuracy and explanation quality.
Then we identify items with an item-item relation- ship to target item i and derive all corresponding I-I triplets
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
-
Boosting Knowledge Graph-based Recommendations through Confidence-Aware Augmentation with Large Language Models
CKG-LLMA augments knowledge graphs with LLM advice and uses learned triplet confidence and dual-view contrastive learning to improve KG-based recommendation accuracy and explanation quality.