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.

翻译：随着大型语言模型的最新进展，链式思考提示等引发推理链的方法已被证明能够提升推理任务的效果。然而，需要多步推理的任务仍对当前最先进的模型构成重大挑战。受束搜索算法启发，我们提出了PathFinder——一种基于树搜索的推理路径生成方法。该方法通过动态解码（借助不同的采样方法和参数）增强多样化的分支生成与多跳推理能力。PathFinder采用约束推理，集成了新颖的质量约束、剪枝与探索方法，从而提升生成效率与质量。此外，它还包含评分与排序功能以优化候选选择。在三个复杂的算术与常识推理任务上，我们的方法平均比竞争基线方法高出6%。该模型能很好地泛化至更长的、未见过的推理链，其复杂度类似于具有大分支因子的束搜索。