大模型对齐与安全

CARE Drive A Framework for Evaluating Reason-Responsiveness of Vision Language Models in Automated Driving

CARE Drive：一种用于评估视觉语言模型在自动驾驶中推理响应性的框架

Lucas Elbert Suryana, Farah Bierenga, Sanne van Buuren, Pepijn Kooij, Elsefien Tulleners, Federico Scari, Simeon Calvert, Bart van Arem, Arkady Zgonnikov

机构 * organization= Department of Transport \& Planning, Faculty of Civil Engineering ； Geosciences, Delft University of Technology ； organization= Department of Cognitive Robotics, Faculty of Mechanical Engineering, Delft University of Technology ； organization= Centre for Meaningful Human Control, Delft University of Technology ； organization= Faculty of Mechanical Engineering, Delft University of Technology , city= Delft , country= The Netherlands 纠错

专题命中 幻觉与事实性 ：alignment(abstract)；safety(abstract)；分类 cs.AI

AI总结 CARE Drive提出了一种评估视觉语言模型在自动驾驶中推理响应性的框架，通过受控上下文变化比较基线和增强模型决策，验证人类原因对决策的影响。

Comments 21 pages, on submission to Transportation Research Part C

Efficient Road Renovation Scheduling under Uncertainty using Lower Bound Pruning

在不确定性下使用下界剪枝进行高效的道路翻新调度

Robbert Bosch, Patricia Rogetzer, Wouter van Heeswijk, Martijn Mes

专题命中 幻觉与事实性 ：safety(abstract)

AI总结 本文提出了一种结合机器学习和遗传算法的混合优化方法，用于在不确定性下高效调度大规模基础设施翻新，通过概率性失效模型和渐进式下界评估方法提高解决方案质量。

Comments 24 pages, 14 figures, submitted to Computer-Aided Civil and Infrastructure Engineering