Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models
机构 * University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校) ; Louisiana State University(路易斯安那州立大学) ; Cisco Research(思科研究)
Comments 8 pages + Appendix
大厂专区
机构 * University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校) ; Louisiana State University(路易斯安那州立大学) ; Cisco Research(思科研究)
Comments 8 pages + Appendix
机构 * University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校) ; Arizona State University(亚利桑那州立大学) ; Cisco(思科)