用图推理辅助生成文献综述，自动提炼论文间关系。
GRASP: Graph-Reasoning Aided Survey Planning for High-Fidelity Related Work Generation
- 构建双层图结构：思想图与论点反驳网络，表示论文间的多粒度关系。
- 通过斯坦纳树剪枝识别核心论文关联，提升综述逻辑性。
- 生成的文献综述与人工撰写高度一致，适用于科研写作助手。
撰写文献综述需要深入理解引用论文之间的关系：它们如何相互支持、挑战或提供不同视角。我们提出图推理辅助的综述规划框架GRASP，结合大模型规划与图算法，自动提取引用论文间的关键关系。该框架采用两层图结构，包含思想图（Graph of Thoughts）和论点-反驳规划网络（Argument-Counterargument Planning Network），在不同粒度上表示论文间的关系，并利用拓扑感知剪枝（斯坦纳树）识别核心论文关联。基于引文分析的评估显示，GRASP生成的文献综述（RWS）在引用的论述角色、意图和分组上与人工撰写的目标高度一致。
原文摘要 · Abstract (English)
Writing a literature review requires a deep understanding of the relationships among cited papers: how they build on, challenge, or offer alternative perspectives to one another. We present Graph-Reasoning Aided Survey Planning (GRASP), a framework combining LLM planning for related work generation with graph algorithms to extract key relationships among cited papers. Our two-layer graph structure consists of a Graph of Thoughts and an Argument-Counterargument Planning Network, representing the cited papers at different levels of granularity, and we apply topology-aware pruning via a Steiner tree to identify the core inter-paper relationships captured in our graph. Our citation analysis-based evaluation shows that GRASP generates related work sections (RWS) that closely match human-written targets in terms of the discourse roles, intents, and grouping of citations.
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。