面向引文图谱的自动演化树生成
Towards Automatic Evolution Tree Generation from Citation Graphs
- Georgia Institute of Technology（佐治亚理工学院）
- Emory University（埃默里大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对现有分类学归纳方法局限于叶节点且忽略时间的问题，提出EvoTree分阶段框架，通过图感知编码器、层次聚类和时间微调生成演化树，在首个覆盖11个AI子领域的基准上取得最优性能。
AI中文摘要：
综述仍是研究者掌握人工智能子领域内方法谱系的主要途径，但其扩展性难以适应当前的论文发表速度。现有的分类学归纳方法大多局限于叶节点且不考虑时间因素；它们倾向于将过渡性论文强行归入成熟的叶节点，并可能在祖先与后代之间造成拓扑倒置。我们提出EvoTree，一种分阶段框架，将概念骨干学习与时间细化解耦：基于图感知编码器与基于分布的层次聚类生成稳定的分类学骨干；随后进行时间微调，在单调路径约束下将边缘论文重新挂接到内部节点；最后通过大语言模型（LLM）处理为概念打标签，而不改变拓扑结构。我们发布了首个针对该任务、覆盖11个人工智能子领域的带标注基准。EvoTree在所有基线中取得了最高的归一化互信息（NMI）和引文方向准确率，并在标注基准上实现了最佳的概念纯度，且是唯一在标注集上具有非平凡边缘论文检测能力的方法。
英文摘要：
Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publication. Existing taxonomy-induction methods are largely leaf-bound and time-agnostic; they tend to force transitional papers into mature leaves and can create topological inversions between ancestors and descendants. We propose EvoTree, a staged framework that decouples conceptual backbone learning from temporal refinement: a graph-aware encoder with distribution-based hierarchical clustering yields a stable taxonomy backbone; temporal fine-tuning then re-attaches marginal papers to internal nodes under monotonic-path constraints; a final LLM pass labels concepts without altering the topology. We release the first annotated benchmark for this task across 11 AI subfields. EvoTree attains the highest NMI and citation-direction accuracy among all baselines and the best concept purity on the annotated benchmark, and is the only method with non-trivial marginal-paper detection on the annotated set.
