Large language models reorganize representational geometry during in-context learning
大型语言模型在上下文学习中重组表征几何结构
机构 * School of Psychological and Brain Sciences, Georgia Tech(佐治亚理工学院心理与脑科学学院) ; Department of Psychology, New York University(纽约大学心理学系) ; Center of Excellence for Computational Cognition, Georgia Tech(佐治亚理工学院计算认知卓越中心) ; Honda Research Institute(本田研究院) ; Departments of Neuroscience and Psychology, The University of Texas at Austin(德克萨斯大学奥斯汀分校神经科学与心理学系)
AI总结 研究大型语言模型在上下文学习中的表征几何重组,发现其性能与任务表征结构相关,并通过原型算法动态调整表征以提高可分性。
Comments Published as a conference paper at COLM 2026