Strategic Over-Parameterization for Generalizable Low-Rank Adaptation
战略性过参数化以实现通用的低秩适应
机构 * School of Fundamental Physics and Mathematical Sciences, Hangzhou Institute for Advanced Study, UCAS, Hangzhou 310024, China(1 基础物理与数学科学学院,杭州先进研究院,UCAS,杭州 310024,中国) ; School of Physical Sciences, University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing 100049, China(2 物理科学学院,中国科学院大学,玉泉路19A号,北京 100049,中国) ; CAS Key Laboratory of Theoretical Physics, Institute of Theoretical Physics, Chinese Academy of Sciences, Beijing 100190, China(3 中国科学院理论物理重点实验室,理论物理研究所,中国科学院,北京 100190,中国) ; School of Physics and Key Laboratory of Quantum State Construction and Manipulation (Ministry of Education), Renmin University of China, Beijing 100872, China(4 物理学院和量子态构造与操控(教育部)重点实验室,中国人民大学,北京 100872,中国)
专题命中 指令微调 :large language model(abstract);language model(abstract);分类 cs.AI、cs.LG
AI总结 本文提出LoRA-Over框架,通过训练时丰富优化景观并推理时压缩,提升低秩适应的泛化能力,实验显示其在多个任务上优于传统LoRA。