思维缓冲区：利用大型语言模型进行思维增强推理

摘要

我们介绍了一种名为“思维缓冲区”（Buffer of Thoughts，BoT）的新颖多功能思维增强推理方法，用于提升大型语言模型（LLMs）的准确性、效率和鲁棒性。具体而言，我们提出了元缓冲区，用于存储一系列信息丰富的高层思维，即从各种任务的问题解决过程中提炼出的思维模板。然后针对每个问题，我们检索相关的思维模板，并自适应地将其实例化为具体的推理结构，以进行高效的推理。为了保证可扩展性和稳定性，我们进一步提出了缓冲区管理器，动态更新元缓冲区，从而随着解决更多任务而增强元缓冲区的容量。我们在10个具有挑战性的推理密集型任务上进行了大量实验，并相较于先前的SOTA方法取得了显著的性能改进：在“24点游戏”上提高了11％，在“几何形状”上提高了20％，在“一步将军”上提高了51％。进一步分析表明，我们的BoT具有出色的泛化能力和模型鲁棒性，而平均仅需多次查询提示方法（例如，思维树/图）成本的12％。值得注意的是，我们发现我们的Llama3-8B+BoT有潜力超越Llama3-70B模型。我们的项目可在以下链接找到：https://github.com/YangLing0818/buffer-of-thought-llm

English

We introduce Buffer of Thoughts (BoT), a novel and versatile thought-augmented reasoning approach for enhancing accuracy, efficiency and robustness of large language models (LLMs). Specifically, we propose meta-buffer to store a series of informative high-level thoughts, namely thought-template, distilled from the problem-solving processes across various tasks. Then for each problem, we retrieve a relevant thought-template and adaptively instantiate it with specific reasoning structures to conduct efficient reasoning. To guarantee the scalability and stability, we further propose buffer-manager to dynamically update the meta-buffer, thus enhancing the capacity of meta-buffer as more tasks are solved. We conduct extensive experiments on 10 challenging reasoning-intensive tasks, and achieve significant performance improvements over previous SOTA methods: 11% on Game of 24, 20% on Geometric Shapes and 51% on Checkmate-in-One. Further analysis demonstrate the superior generalization ability and model robustness of our BoT, while requiring only 12% of the cost of multi-query prompting methods (e.g., tree/graph of thoughts) on average. Notably, we find that our Llama3-8B+BoT has the potential to surpass Llama3-70B model. Our project is available at: https://github.com/YangLing0818/buffer-of-thought-llm

思维缓冲区：利用大型语言模型进行思维增强推理

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

摘要

Summary

Support

Support