Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing
无需训练即可清晰感知:减轻多模态大语言模型在遥感中的幻觉
机构 * School of Computer Science, Wuhan University, China(武汉大学计算机学院) ; Zhongguancun Academy, China(中关村学院) ; School of Computer Science, Chongqing University, China(重庆大学计算机学院)
专题命中 医疗多模态 :diagnosis(abstract);分类 cs.CV
AI总结 RADAR通过利用多模态大语言模型的内在注意力,无需训练即可减少遥感视觉问答中的事实性和逻辑性幻觉。