发表机构
Microsoft（微软公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对大语言模型生成同质化逻辑的问题，构建了映射特定创作者的烹饪执行图数据集，提出结构化两阶段模型，可精准刻画与生成创作者的过程风格，集成方法能融合语义推理与拓扑控制优势。
AI 中文摘要
尽管大语言模型（LLMs）拥有丰富的零样本过程知识，但其生成同质化逻辑的倾向常掩盖了个体人类创作者独特、特异的执行过程。本文研究如何从非结构化数据中计算性地发现过程人设。为此，我们引入ViralRecipesTrans，这是一个从热门烹饪视频 transcript 中提取的、与过程对齐的执行流程图数据集，且明确映射到特定创作者。我们将过程风格计量学形式化为图学习与过程发现任务，揭示了一个基本二元性：传统词汇分类器会因语义泄漏而过拟合，而离散拓扑指标可成功捕捉创作者工作流的刚性物理约束。基于此刻画，我们将框架扩展为一项新的生成任务——为未知菜品预测创作者精确的结构执行图。我们揭示了风格生成中全局宏观规划与局部结构执行之间的基本二分。结果表明，少样本LLMs在语义分配上占优，但存在持续的宏观规划缺陷；而我们的结构化两阶段模型通过刚性马尔可夫先验实现了更优的拓扑控制。此外，过程生成的集成方法结合了双方的优势，动态融合全局语义推理与局部拓扑特征，以自动化个性化工作流的发现与生成。
英文摘要
While large language models (LLMs) possess vast zero-shot procedural knowledge, their tendency to produce homogenized logic often obscures the unique, idiosyncratic execution processes of individual human creators. In this paper, we investigate the computational discovery of procedural personas from unstructured data. To achieve this, we introduce ViralRecipesTrans, a new dataset of procedurally aligned execution flow graphs extracted from popular culinary video transcripts and explicitly mapped to specific creators. We formulate procedural stylometry as a graph learning and process discovery task, revealing a fundamental duality: while traditional lexical classifiers overfit via semantic leakage, discrete topological metrics successfully capture the rigid physical constraints of a creator's workflow. Building upon this characterization, we extend our framework into a novel generative task--predicting a creator's exact structural execution graph for unseen dishes. We expose a fundamental dichotomy in style generation between global macro-planning and local structural execution. Our results demonstrate that few-shot LLMs dominate semantic assignment but suffer from persistent macro-planning deficits, whereas our structured two-stage model achieves superior topological control via rigid Markovian priors. Together, an ensemble approach to procedural generation combines the strengths from both sides, dynamically synthesizing global semantic reasoning with localized topological footprints to automate the discovery and generation of personalized workflows.
CommentsAccepted at the 29th International Conference on Discovery Science (DS 2026). 15 pages, 2 figures
