DynaThink：快还是慢？一种面向大语言模型的动态决策框架
DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models
AI总结：
本文提出DynaThink动态决策框架，使大语言模型能根据任务复杂度在快速思维链与慢速多路径验证推理之间自主选择，从而在五个推理基准上同时提升效率与效果。
摘要：
大语言模型（LLMs）通过流行的思维链（CoT）提示在多种推理任务中展现出了涌现能力。然而，这种简单且快速的CoT方法在处理复杂问题时常常遇到局限，而一种考虑多条推理路径并仔细验证每一步的彻底方法则会导致推理速度变慢。本文应对的挑战是使LLMs能够自主选择快速与慢速推理方法，从而同时优化效率和效果。我们引入了一个动态决策框架，将任务划分为两条不同的路径：“快速”路径适用于LLM能够迅速识别出高置信度解决方案的任务；“慢速”路径分配给LLM认为复杂、对即时解决方案置信度较低且需要更多推理路径进行验证的任务。在五个流行的推理基准上的实验证明了DynaThink相对于基线方法的优越性。
英文摘要：
Large language models (LLMs) have demonstrated emergent capabilities across diverse reasoning tasks via popular Chains-of-Thought (COT) prompting. However, such a simple and fast COT approach often encounters limitations in dealing with complicated problems, while a thorough method, which considers multiple reasoning pathways and verifies each step carefully, results in slower inference. This paper addresses the challenge of enabling LLMs to autonomously select between fast and slow inference methods, thereby optimizing both efficiency and effectiveness. We introduce a dynamic decision-making framework that categorizes tasks into two distinct pathways: 'Fast', designated for tasks where the LLM quickly identifies a high-confidence solution, and 'Slow', allocated for tasks that the LLM perceives as complex and for which it has low confidence in immediate solutions as well as requiring more reasoning paths to verify. Experiments on five popular reasoning benchmarks demonstrated the superiority of the DynaThink over baselines.
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。
