PPL
Ziyue Wang
Papers (4)
The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter UpdatesLeveraging Error Diversity in Group Rollouts for Reinforcement LearningWhen Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM AgentsDistributional Spectral Diagnostics for Localizing Grokking Transitions