DAGverse: 从科学论文构建文档导向的语义DAG
DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers
AI总结：
本文提出DAGverse框架，通过科学论文中的显式DAG图和文本上下文，自动构建文档导向的语义DAG，提升DAG分类和标注的精度。
摘要：
有向无环图（DAG）被广泛用于科学和技术领域表示结构化知识。然而，现实世界中的DAG数据集仍然稀缺，因为构建它们通常需要领域文档的专家解释。我们研究Doc2SemDAG的构建：从文档及其引用证据和上下文恢复一个优选的语义DAG。此问题具有挑战性，因为文档可能有多种合理的抽象，所期望的结构通常是隐含的，支持证据分散在文本、方程、图注和图表中。为了解决这些挑战，我们利用包含显式DAG图的科学论文作为自然的监督来源。在此设置中，DAG图提供DAG结构，而伴随的文本提供上下文和解释。我们引入DAGverse，一种从在线科学论文构建文档导向语义DAG的框架。其核心组件，DAGverse-Pipeline，是一个半自动系统，通过图分类、图重建、语义定位和验证来生成高精度的语义DAG示例。作为案例研究，我们测试该框架用于因果DAG，并发布DAGverse-1，一个包含108个专家验证的语义DAG的数据集，具有图级、节点级和边级证据。实验显示，DAGverse-Pipeline在DAG分类和标注上优于现有视觉-语言模型。DAGverse为文档导向的DAG基准提供了基础，并为基于现实证据的结构推理研究开辟了新方向。
英文摘要：
Directed Acyclic Graphs (DAGs) are widely used to represent structured knowledge in scientific and technical domains. However, datasets for real-world DAGs remain scarce because constructing them typically requires expert interpretation of domain documents. We study Doc2SemDAG construction: recovering a preferred semantic DAG from a document together with the cited evidence and context that explain it. This problem is challenging because a document may admit multiple plausible abstractions, the intended structure is often implicit, and the supporting evidence is scattered across prose, equations, captions, and figures. To address these challenges, we leverage scientific papers containing explicit DAG figures as a natural source of supervision. In this setting, the DAG figure provides the DAG structure, while the accompanying text provides context and explanation. We introduce DAGverse, a framework for constructing document-grounded semantic DAGs from online scientific papers. Its core component, DAGverse-Pipeline, is a semi-automatic system designed to produce high-precision semantic DAG examples through figure classification, graph reconstruction, semantic grounding, and validation. As a case study, we test the framework for causal DAGs and release DAGverse-1, a dataset of 108 expert-validated semantic DAGs with graph-level, node-level, and edge-level evidence. Experiments show that DAGverse-Pipeline outperforms existing Vision-Language Models on DAG classification and annotation. DAGverse provides a foundation for document-grounded DAG benchmarks and opens new directions for studying structured reasoning grounded in real-world evidence.
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。
