用可视化图结构帮助大模型组织推理，提升多跳问答能力。
Visual Graph Scaffolds for Structural Reasoning in Large Language Models
- 将思维导图转为视觉化图结构辅助模型推理
- 无直接答案提示时，文本化图结构效果下降60%以上
- 适合需要结构化推理的复杂问答任务
图结构常被用作外部知识增强大语言模型的结构化推理，通常在测试时提供。本文提出新视角：图的价值不仅在于提供信息，更在于组织推理过程。受人类使用图状思维导图梳理复杂思路的启发，我们探索图作为内部推理辅助的潜力。在多跳问答任务中，将教师提供的推理轨迹重写为图状思维导图，并用于指导学生模型。实验发现明显模态差异：当图结构被扁平化为文本后，若移除直接答案提示，推理效率与准确率均显著下降。而视觉图引导在无直接线索时仍有效，且在监督微调和基于KL散度的蒸馏后优势持续存在。结果表明，图不仅是外部知识载体，更应被视为组织推理的视觉支架。
原文摘要 · Abstract (English)
Graphs have been used to enhance large language models (LLMs) for structured reasoning, mostly as external knowledge sources are provided to models at test time. In this paper, we take a different view: the value of graphs for LLMs lie not only in supplying information, but also in organizing reasoning. Inspired by how humans use graph-structured mind maps to organize branching and converging thoughts, we ask whether graphs can serve as an internal form of reasoning assistance. We study this question on multi-hop question answering tasks, where teacher-provided reasoning traces are rewritten as graph mind maps and used to guide a student model. Our experiments reveal a clear modality gap. When graph structures are flattened into text, their benefits become limited once direct answer hints are removed. Under this abstract guidance setting, both reasoning efficiency and answer quality degrade substantially. In contrast, visual graph guidance remains effective without direct answer clues, and its advantage persists after supervised fine-tuning and KL-based distillation. The above findings support the claim that graphs should be studied not only as external knowledge structures for LLMs, but also as visual scaffolds for organizing reasoning.
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。