FlowPlan-G2P：一种将科学论文转化为专利描述的结构化生成框架
FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into Patent Descriptions
AI总结：
提出FlowPlan-G2P图介导生成框架，通过概念图归纳、章节级规划和图条件生成三阶段分解，将科学论文转化为符合专利规范的描述，在领域评估中优于大型专有模型。
摘要：
由于科学论文与专利在修辞和结构上的根本差异，从科学论文生成专利描述具有挑战性。现有方法将其视为表面改写，未能捕捉专利起草中固有的层次推理和法定约束。我们提出FlowPlan-G2P，一种图介导的生成框架，将该转换分解为三个阶段：（1）概念图归纳，将技术实体和功能依赖提取为有向图；（2）章节级规划，将图划分为与规范专利章节对齐的连贯子图；（3）图条件生成，基于章节特定子图合成符合法律要求的段落。在专家验证基准上的实验表明，标准NLG指标系统性偏好法律不合规输出而非有效专利描述，这促使我们进行领域特定评估。在该评估下，使用开放权重骨干的FlowPlan-G2P始终优于原始专有模型，表明结构化分解比模型规模更能决定质量。
英文摘要：
Generating patent descriptions from scientific papers is challenging due to fundamental rhetorical and structural disparities between the two genres. Existing approaches treat this as surface-level rewriting, failing to capture the hierarchical reasoning and statutory constraints inherent in patent drafting. We propose FlowPlan-G2P, a graph-mediated generation framework that decomposes this transformation into three stages: (1) Concept Graph Induction, extracting technical entities and functional dependencies into a directed graph; (2) Section-level Planning, partitioning the graph into coherent subgraphs aligned with canonical patent sections; and (3) Graph-Conditioned Generation, synthesizing legally compliant paragraphs conditioned on section-specific subgraphs. Experiments on expert-validated benchmarks reveal that standard NLG metrics systematically favor legally non-compliant outputs over valid patent descriptions, motivating our domain-specific evaluation. Under this evaluation, FlowPlan-G2P with an open-weight backbone consistently outperforms vanilla proprietary models, demonstrating that structured decomposition is a stronger determinant of quality than model scale.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
