PPL
Xin Geng
Papers (7)
Energy-Structured Low-Rank Adaptation for Continual LearningBeyond Binary Success: A Diagnostic Meta-Evaluation Framework for Fine-Grained ManipulationXPERT: Expert Knowledge Transfer for Effective Training of Language ModelsBeyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label EnhancementChain-based Distillation for Effective Initialization of Variable-Sized Small Language ModelsUnderstanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation TransitionsLearngene Search Across Multiple Datasets for Building Variable-Sized Models