yonad2008/predict_xgb_phi4_14b

XGBoost Jailbreak Prediction Model: phi4:14b

XGBoost + TF-IDF (+ optional TruncatedSVD) classifier for unsafe/jailbreak likelihood in multi-turn conversations.

Evaluation Results (best fold: 1)

Training Details

• —Target model: phi4:14b
• —Datasets: harmful_behaviors
• —K-Folds: 5
• —Input format: single turn: category + strategy_name + one TURN line
• —TF-IDF ngram_range: (1, 1)
• —TF-IDF max_features: 120000
• —TruncatedSVD: enabled True, requested n_components=1024
• —XGBoost n_estimators: 971
• —XGBoost learning_rate: 0.045325359791945935
• —XGBoost max_depth: 7

Dataset Size (training samples)

Prepared turn-level samples: 1611 (unsafe: 119, safe: 1492)