CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation Paper • 2511.18889 • Published Nov 24, 2025 • 1
KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning Paper • 2506.02208 • Published Jun 2, 2025 • 3