Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks
潜在链式思考模型是否分步思考?对序列推理任务的机制研究
机构 * Institute for Computational and Mathematical Engineering, Stanford University, Stanford, USA(计算与数学工程研究所,斯坦福大学) ; MOE Key Lab of Computational Linguistics, Peking University, Beijing, China(教育部计算语言学重点实验室,北京大学) ; Beijing Academy of Artificial Intelligence, Beijing, China(北京人工智能研究院)
AI总结 本文研究了CODI模型在序列推理任务中的机制,揭示了潜在链式思考在不同跳数下的计算路径及可靠性问题。
Comments 20 pages, 14 figures