問題樹：通過組合性改進結構化問題解決

Tree of Problems: Improving structured problem solving with compositionality

October 9, 2024

作者: Armel Zebaze, Benoît Sagot, Rachel Bawden

cs.AI

摘要

大型語言模型（LLMs）通過上下文學習在多個任務上展現出卓越的性能。對於需要逐步思考的複雜推理任務，思維鏈（CoT）提示在與自我一致性結合時取得了令人印象深刻的成果。然而，某些任務對於LLMs來說仍然特別難以解決。思維樹（ToT）和思維圖（GoT）作為替代方案應運而生，將複雜問題劃分為子問題路徑。在本文中，我們提出了問題樹（ToP），這是ToT的簡化版本，我們假設對於可以劃分為相同子任務的複雜任務，這種方法可能效果更好。我們的實證結果表明，我們的方法優於ToT和GoT，並且在複雜推理任務上表現優於CoT。本文的所有代碼都可以在以下鏈接公開獲取：https://github.com/ArmelRandy/tree-of-problems。

English

Large Language Models (LLMs) have demonstrated remarkable performance across multiple tasks through in-context learning. For complex reasoning tasks that require step-by-step thinking, Chain-of-Thought (CoT) prompting has given impressive results, especially when combined with self-consistency. Nonetheless, some tasks remain particularly difficult for LLMs to solve. Tree of Thoughts (ToT) and Graph of Thoughts (GoT) emerged as alternatives, dividing the complex problem into paths of subproblems. In this paper, we propose Tree of Problems (ToP), a simpler version of ToT, which we hypothesise can work better for complex tasks that can be divided into identical subtasks. Our empirical results show that our approach outperforms ToT and GoT, and in addition performs better than CoT on complex reasoning tasks. All code for this paper is publicly available here: https://github.com/ArmelRandy/tree-of-problems.