Zhange Zhang

AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing

Conflict-Aware Knowledge Editing in the Wild: Semantic-Augmented Graph Representation for Unstructured Text

Token-Aware Inference-Time Intervention for Large Language Model Alignment

Lexical Diversity-aware Relevance Assessment for Retrieval-Augmented Generation