PPL
Rui Miao
Papers (5)
Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External DiscrepancyOPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM ReasoningAre Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation DetectionPrecision Physical Activity Prescription via Reinforcement Learning for Functional ActionsTOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing