开始发作
发表于 2025-3-23 10:27:29
http://reply.papertrans.cn/83/8236/823568/823568_11.png
有发明天才
发表于 2025-3-23 16:26:38
http://reply.papertrans.cn/83/8236/823568/823568_12.png
不幸的人
发表于 2025-3-23 18:20:25
Paul H. Robinson,John D. Stephenson,Timothy H. Moranfferent conditions, manipulating the transparency in a team. The results showed an interaction effect between the agents’ strategy and transparency on trust, group identification and human-likeness. Our results suggest that transparency has a positive effect in terms of people’s perception of trust,
Flat-Feet
发表于 2025-3-24 01:00:29
http://reply.papertrans.cn/83/8236/823568/823568_14.png
bile648
发表于 2025-3-24 02:24:43
http://reply.papertrans.cn/83/8236/823568/823568_15.png
SHOCK
发表于 2025-3-24 07:53:30
Rebecca M. Prussng exploitation of ML-based approaches generated opaque systems, which are nowadays no longer socially acceptable—calling for eXplainable AI (XAI). Such a problem is exacerbated when IS tend to approach safety-critical scenarios. This paper highlights the need for on-time explainability. In particul
Pander
发表于 2025-3-24 11:10:28
F. Javier Garcia-Ladona,Guadalupe Mengod,José M. Palacios agents using two different algorithms which automatically generate different explanations for agent actions. Quantitative analysis of three user groups (n = 20, 25, 20) in which users detect the bias in agents’ decisions for each explanation type for 15 test data cases is conducted for three differ
Cpap155
发表于 2025-3-24 18:09:09
Sandra E. Loughlin,Frances M. Leslie agents using two different algorithms which automatically generate different explanations for agent actions. Quantitative analysis of three user groups (n = 20, 25, 20) in which users detect the bias in agents’ decisions for each explanation type for 15 test data cases is conducted for three differ
对手
发表于 2025-3-24 19:38:56
Edythe D. London,Stephen R. Zukin agents using two different algorithms which automatically generate different explanations for agent actions. Quantitative analysis of three user groups (n = 20, 25, 20) in which users detect the bias in agents’ decisions for each explanation type for 15 test data cases is conducted for three differ
AMITY
发表于 2025-3-25 00:50:57
Ann Tempelng exploitation of ML-based approaches generated opaque systems, which are nowadays no longer socially acceptable—calling for eXplainable AI (XAI). Such a problem is exacerbated when IS tend to approach safety-critical scenarios. This paper highlights the need for on-time explainability. In particul