DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models
This addresses the problem of balancing speed and accuracy in LLM reasoning for users needing efficient task handling, though it is incremental as it builds on existing prompting methods.
The paper tackles the challenge of enabling large language models to autonomously choose between fast and slow inference methods to optimize efficiency and effectiveness, achieving superior performance on five reasoning benchmarks.
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.