探索大模型如何利用示例结构构建多步推理证明
Exploring the Role of Reasoning Structures for Constructing Proofs in Multi-Step Natural Language Reasoning with Large Language Models
- 通过结构化示例和剪枝提升推理步骤组织能力
- 在多步推理任务中显著改善了证明结构的生成质量
- 适合研究模型可解释性与复杂推理的学者
在执行复杂的多步推理任务时，大型语言模型（LLMs）能否生成结构化的中间推理步骤，对确保模型真正完成所需推理并提升可解释性至关重要。本文聚焦于一个核心问题：当前最先进的通用大模型是否能利用少量示例中的结构信息，通过上下文学习（in-context learning）更好地构建证明结构。研究重点在于结构感知的示范（structure-aware demonstration）与结构感知的剪枝（structure-aware pruning）。实验表明，这两种方法均能有效提升性能。文章还提供了详细分析，以深入理解其结果。
原文摘要 · Abstract (English)
When performing complex multi-step reasoning tasks, the ability of Large Language Models (LLMs) to derive structured intermediate proof steps is important for ensuring that the models truly perform the desired reasoning and for improving models' explainability. This paper is centred around a focused study: whether the current state-of-the-art generalist LLMs can leverage the structures in a few examples to better construct the proof structures with \textit{in-context learning}. Our study specifically focuses on structure-aware demonstration and structure-aware pruning. We demonstrate that they both help improve performance. A detailed analysis is provided to help understand the results.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。