Boosting of Thoughts：使用大型语言模型进行试错式问题解决
Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
AI总结：
本文提出 BoT 自动化提示框架，通过迭代探索、评估思维树并基于错误分析修正提示，使 GPT-4 和 Llama2 在复杂数学问题上取得更优或相当的解决率。
摘要：
大型语言模型（LLM）在广泛问题上的推理表现关键依赖于思维链提示，即在提示中提供若干思维链演示作为范例。近期工作（例如 Tree of Thoughts）指出，在复杂问题解决的推理步骤选择中，探索和自我评估具有重要意义。本文提出 Boosting of Thoughts（BoT），这是一个用于使用 LLM 解决问题的自动化提示框架：它通过迭代探索和自我评估许多思维树，以获得一组试错推理经验，这些经验将作为一种新的提示形式来解决复杂问题。BoT 从无需示例的简单提示开始，迭代探索并评估大量推理步骤；更重要的是，它利用 LLM 对这些步骤得出的错误分析来显式修正提示，进而增强推理步骤生成，直到获得最终答案。我们在大量复杂数学问题上使用 GPT-4 和 Llama2 进行的实验表明，与其他先进提示方法相比，BoT 始终取得更高或相当的问题解决率。
英文摘要：
The reasoning performance of Large Language Models (LLMs) on a wide range of problems critically relies on chain-of-thought prompting, which involves providing a few chain of thought demonstrations as exemplars in prompts. Recent work, e.g., Tree of Thoughts, has pointed out the importance of exploration and self-evaluation in reasoning step selection for complex problem solving. In this paper, we present Boosting of Thoughts (BoT), an automated prompting framework for problem solving with LLMs by iteratively exploring and self-evaluating many trees of thoughts in order to acquire an ensemble of trial-and-error reasoning experiences, which will serve as a new form of prompting to solve the complex problem. Starting from a simple prompt without requiring examples, BoT iteratively explores and evaluates a large collection of reasoning steps, and more importantly, uses error analysis obtained from the LLM on them to explicitly revise prompting, which in turn enhances reasoning step generation, until a final answer is attained. Our experiments with GPT-4 and Llama2 across extensive complex mathematical problems demonstrate that BoT consistently achieves higher or comparable problem-solving rates than other advanced prompting approaches.
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。
