链式思维与潜在思维的正式比较
A Formal Comparison Between Chain of Thought and Latent Thought
AI总结：
本文对比了链式思维与潜在思维，发现潜在思维在并行计算上更高效，而链式思维能通过随机解码实现近似计数与采样。
摘要：
链式思维（CoT）通过显式生成中间标记来激发大语言模型的推理能力。相比之下，潜在思维推理直接在连续潜在空间中运作，使计算超越离散语言表示。尽管两者都利用迭代计算，但它们的比较能力仍待深入研究。本文通过正式分析表明，潜在思维比本质上顺序的CoT具有更高效的并行计算能力。相反，CoT通过随机解码实现近似计数和采样。这些分离表明了哪些任务更适合深度驱动的递归，从而为选择推理范式提供了实用指导。
英文摘要：
Chain of thought (CoT) elicits reasoning in large language models by explicitly generating intermediate tokens. In contrast, latent thought reasoning operates directly in the continuous latent space, enabling computation beyond discrete linguistic representations. While both approaches exploit iterative computation, their comparative capabilities remain underexplored. In this work, we present a formal analysis showing that latent thought admits more efficient parallel computation than inherently sequential CoT. In contrast, CoT enables approximate counting and sampling through stochastic decoding. These separations suggest the tasks for which depth-driven recursion is more suitable, thereby offering practical guidance for choosing between reasoning paradigms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
