通过新框架提升大型语言模型的逻辑推理能力：Graph of Thought
Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought
AI总结：
本文提出 Graph of Thoughts（GoT）提示框架，通过图结构组织推理过程，在24点游戏、高次方程和递归序列任务上显著提升 GPT-4 及 ToT 的逻辑推理准确率。
摘要：
近期，诸如 GPT-4 等大规模模型的进展展现出其在处理标准查询方面的卓越能力。然而，当面对需要多步逻辑推理的复杂问题时，它们的准确率会急剧下降。当前研究已经探索了提示工程领域，以增强这些模型的推理能力。本文公布了一种开创性的提示技术，称为 Graph of Thoughts（GoT）。通过在三项难度递增的挑战上进行测试——24点游戏、高次多项式方程求解以及递归序列公式推导——我们的方法优于 GPT-4，在各项任务上分别实现了 89.7%、86% 和 56% 的准确率提升。此外，与最先进（SOTA）的提示方法 Tree of Thought（ToT）相比，我们的方法取得了平均 23%、24% 和 15% 的准确率提升。
英文摘要：
Recent advancements in large-scale models, such as GPT-4, have showcased remarkable capabilities in addressing standard queries. However, when facing complex problems that require multi-step logical reasoning, their accuracy dramatically decreases. Current research has explored the realm of \textit{prompting engineering} to bolster the inferential capacities of these models. Our paper unveils a pioneering prompting technique, dubbed \textit{Graph of Thoughts (GoT)}. Through testing on a trio of escalating challenges: the 24-point game, resolution of high-degree polynomial equations, and derivation of formulas for recursive sequences, our method outperformed GPT-4, achieving accuracy improvements of $89.7\%$, $86\%$, and $56\%$ for each respective task. Moreover, when juxtaposed with the state-of-the-art (SOTA) prompting method, \textit{Tree of Thought (ToT)}, our approach registered an average accuracy boost of $23\%$, $24\%$, and $15\%$.
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。
