Training RAG generators on contrastive knowledge-graph pairs with weighted DPO improves average exact-match by 1.8 to 4.2 points across three model sizes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG
Training RAG generators on contrastive knowledge-graph pairs with weighted DPO improves average exact-match by 1.8 to 4.2 points across three model sizes.