{ "Exact-Match": 0.038, "Token-F1": 0.4456, "BLEU-4": 0.1818, "BERTScore-F1": 0.5342, "Safety-Score": 0.8309, "Halluc-Rate": 0.328, "Overconf-Rate": 0.0, "Abstention-Rate": 0.0, "Mean-Confidence": 0.7759, "ECE": 0.7359, "N": 500 }