会员服务
Assessing Reliability of Symbol Detection in Concept Bottleneck Models
Arxiv
0+阅读 · 6月15日
Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
Arxiv
0+阅读 · 5月1日
Towards Faithful Multimodal Concept Bottleneck Models
Towards Faithful Multimodal Concept Bottleneck Models
Arxiv
0+阅读 · 3月13日
参考链接
微信扫码咨询专知VIP会员
Top