PPL
Yunfang Wu
Papers (4)
ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral ValidationADWIN: Adaptive Windows for Horizon-Aware On-Policy DistillationTrait-Aware Policy Optimization for Autoregressive Multi-Trait Essay ScoringNot All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoning