AURORA: Asymmetry and Update-Induced Rotation for Robust Hallucination Detection in Large Language Models
AURORA:用于大型语言模型中鲁棒幻觉检测的不对称性与更新诱导旋转
机构 * School of Artificial Intelligence, Beihang University, China(北京航空航天大学人工智能学院) ; Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, China(北京航空航天大学未来区块链与隐私计算先进创新中心)
AI总结 提出AURORA框架,利用权重梯度动态(不对称性和旋转比)检测LLM幻觉,跨模型和数据集表现鲁棒。