RAG-Zeval uses rule-guided RL with ranking rewards on synthetic responses to train a 7B model that evaluates RAG faithfulness and correctness competitively with 70B-class judges.
Ferrara, Ethan-Tonic, and O
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
-
RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning
RAG-Zeval uses rule-guided RL with ranking rewards on synthetic responses to train a 7B model that evaluates RAG faithfulness and correctness competitively with 70B-class judges.