In-context superposition: human-like working memory interference in large language models
类人工作记忆干扰在大语言模型中
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) ; Department of Cognitive Science, Indiana University Bloomington(印第安纳大学布卢明顿分校认知科学系) ; Honda Research Institute(本田研究所) ; Center of Excellence for Computational Cognition, Georgia Tech(佐治亚理工学院计算认知卓越中心) ; 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和心理学系)
AI总结 研究发现大语言模型在工作记忆任务中存在干扰限制,其表现与人类相似,且通过抑制无关信息实现有效记忆检索。
Comments Published as a conference paper at COLM 2026