路径导航器：在多步推理路径上进行引导式搜索

摘要

随着大型语言模型的最新进展，诸如思维链提示等方法已被证明可以改善推理任务的结果。然而，需要多步推理的任务仍然对最先进的模型构成重大挑战。受波束搜索算法启发，我们提出了PathFinder，一种基于树搜索的推理路径生成方法。通过整合动态解码，利用不同的采样方法和参数实现了多样的分支和多跳推理。利用约束推理，PathFinder整合了新颖的质量约束、修剪和探索方法，以提高生成的效率和质量。此外，它包括评分和排名特性以改善候选选择。我们的方法在三个复杂的算术和常识推理任务上平均优于竞争基线6%。我们的模型对于更长、未知的推理链具有很好的泛化能力，反映出与大分支因子的波束搜索类似的复杂性。

English

With recent advancements in large language models, methods like chain-of-thought prompting to elicit reasoning chains have been shown to improve results on reasoning tasks. However, tasks that require multiple steps of reasoning still pose significant challenges to state-of-the-art models. Drawing inspiration from the beam search algorithm, we propose PathFinder, a tree-search-based reasoning path generation approach. It enhances diverse branching and multi-hop reasoning through the integration of dynamic decoding, enabled by varying sampling methods and parameters. Using constrained reasoning, PathFinder integrates novel quality constraints, pruning, and exploration methods to enhance the efficiency and the quality of generation. Moreover, it includes scoring and ranking features to improve candidate selection. Our approach outperforms competitive baselines on three complex arithmetic and commonsense reasoning tasks by 6% on average. Our model generalizes well to longer, unseen reasoning chains, reflecting similar complexities to beam search with large branching factors.

路径导航器：在多步推理路径上进行引导式搜索

PathFinder: Guided Search over Multi-Step Reasoning Paths

摘要

Support