用图学习让大模型自主推理，无需调参也能提升解题能力
Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning
- 把问题推理过程建模为图，用大模型动态生成每一步
- 在多个任务上显著提升推理准确率，且无需额外训练
- 适合需要灵活推理的场景，如数学、逻辑题求解
大语言模型在多个领域取得显著进展，但仍面临训练成本高和复杂推理能力不足的问题。现有方法虽通过结构化范式扩展了推理能力，但多依赖任务特定提示和预设推理流程，限制了灵活性与泛化性。为此，本文提出一种新框架，利用图学习实现大模型更灵活、自适应的推理能力。具体而言，将问题的推理过程建模为图结构，并采用基于大模型的图学习方法，引导每一步推理的自适应生成。为进一步增强模型适应性，引入图神经网络（GNN）模块对生成的推理过程进行表示学习，实现对模型与提示的实时调整。实验结果表明，该方法在不需额外训练或任务特定提示设计的前提下，显著提升了多个任务上的推理性能。代码已开源：https://github.com/zch65458525/L2T。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have achieved remarkable success across various domains. However, they still face significant challenges, including high computational costs for training and limitations in solving complex reasoning problems. Although existing methods have extended the reasoning capabilities of LLMs through structured paradigms, these approaches often rely on task-specific prompts and predefined reasoning processes, which constrain their flexibility and generalizability. To address these limitations, we propose a novel framework that leverages graph learning to enable more flexible and adaptive reasoning capabilities for LLMs. Specifically, this approach models the reasoning process of a problem as a graph and employs LLM-based graph learning to guide the adaptive generation of each reasoning step. To further enhance the adaptability of the model, we introduce a Graph Neural Network (GNN) module to perform representation learning on the generated reasoning process, enabling real-time adjustments to both the model and the prompt. Experimental results demonstrate that this method significantly improves reasoning performance across multiple tasks without requiring additional training or task-specific prompt design. Code can be found in https://github.com/zch65458525/L2T.
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。