Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published 3 days ago • 123
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published 3 days ago • 123
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs Paper • 2505.13529 • Published 19 days ago • 11
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs Paper • 2505.13529 • Published 19 days ago • 11
Prompt-Driven LLM Safeguarding via Directed Representation Optimization Paper • 2401.18018 • Published Jan 31, 2024 • 1