{ "Exact-Match": 0.04, "Token-F1": 0.4967, "BLEU-4": 0.2025, "BERTScore-F1": 0.5817, "Safety-Score": 0.8511, "Halluc-Rate": 0.368, "Overconf-Rate": 0.0, "Abstention-Rate": 0.002, "Mean-Confidence": 0.7258, "ECE": 0.6838, "N": 500 }