Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding
"幻觉消除" 相关文章
Fact Grounded Attention: Eliminating Hallucination in Large Language Models Through Attention Level Knowledge Integration
Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation
