PPL
Bing Wang
Papers (6)
Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning DistillationAre Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation DetectionPrefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy DistillationA Hybrid Tucker-LSTM Tensor Network Model for SOC Prediction in Electric VehiclesR$^3$L: Reasoning 3D Layouts from Relative Spatial RelationsDecomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning