3 accepted papers
Retrieval-Augmented Generation (RAG) enhances the quality of question answering by integrating external knowledge with internal knowledge. A robust RAG system needs to precisely regulate the dependence of the response on the two types of knowledge. The recently proposed context-aware contrastive dec
LLM unlearning aims to remove sensitive or harmful information within the model, thus reducing the potential risk of generating unexpected information. However, existing Preference Optimization (PO)-based unlearning methods suffer two limitations. First, their rigid reward setting limits the effect…
Large Vision-Language models (LVLMs) have demonstrated remarkable performance in a wide range of vision-language tasks as an efficient input/output system. However, the lack of adversarial robustness at the input side and the widespread hallucination phenomenon at the output side significantly under…