共计 148 篇文章
2026
2026年多模态大模型幻觉（Multimodal LLM Hallucination）论文精读
ThinkTrap： Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking
Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
Harnessing the Universal Geometry of Embeddings
Constructing Unlearnable Data with Solely Linear Classifiers
规模化安全：大型模型与智能体安全的综合调查
Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
Small LLMs Are Weak Tool Learners： A Multi-LLM Agen
KVSmooth： Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing
HALLUCINATION-AWARE INTERMEDIATE REPRESENTATION EDIT IN LARGE VISION-LANGUAGE MODELS