PathFinder：導引式多步推理路徑搜索

摘要

隨著大型語言模型的最新進展，像是思維鏈提示這樣的方法已被證明能夠改善推理任務的結果。然而，需要多步推理的任務仍然對最先進的模型構成重大挑戰。受束狹搜索演算法的啟發，我們提出了PathFinder，一種基於樹搜索的推理路徑生成方法。通過整合動態解碼，利用不同的抽樣方法和參數，它增強了多樣分支和多跳推理。使用受限推理，PathFinder整合了新穎的質量約束、修剪和探索方法，以增強生成的效率和質量。此外，它包括評分和排名功能，以改善候選選擇。我們的方法在三個複雜的算術和常識推理任務上平均超越競爭基準6%。我們的模型對於更長、未見的推理鏈具有良好的泛化能力，反映出與具有大分支因子的束狹搜索相似的複雜性。

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.

PathFinder：導引式多步推理路徑搜索

PathFinder: Guided Search over Multi-Step Reasoning Paths

摘要

Support