Decoupled Alignment for Robust Plug-and-Play Adaptation
用于鲁棒即插即用适应的解耦对齐
机构 * Northwestern University(西北大学) ; New York University Abu Dhabi(纽约大学阿布扎克分校) ; Stanford University(斯坦福大学) ; Texas A&M University(德克萨斯农工大学) ; University of California, Los Angeles(加州大学洛杉矶分校) ; Illinois Institute of Technology(伊利诺伊理工学院)
AI总结 研究提出无需训练的大语言模型对齐方法,利用知识蒸馏提取对齐信号,经模型融合实现即插即用的对齐校正,采用增量调试识别关键知识组件,在有害问题数据集上显著提升防御成功率,且不损性能。
Comments Revised to correct the Acknowledgments section. Previous versions inadvertently included acknowledgments of NSF and NIH awards that did not support this work. Those funding acknowledgments have been removed. The technical content, results, and conclusions are unchanged