arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.14856cs.CLcs.AI

气候原因：气候报告中的复杂和隐含因果结构

ClimateCause: Complex and Implicit Causal Structures in Climate Reports

Department of Computer Science, KU Leuven, Belgium（比利时库勒芬大学计算机科学系）；Department of Electronics and Information Systems, Ghent University, Belgium（比利时根特大学电子与信息系统系）；Institute of Argumentation, Linguistics, and Semiotics (IALS), Università della Svizzera italiana, Switzerland（瑞士意大利大学论证、语言学与象征学研究所）

Liesbeth Allein, Nataly Pineda-Castañeda, Andrea Rocci, Marie-Francine Moens

备注：
Accepted to ACL 2026 [Findings]
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出ClimateCause数据集，通过专家标注揭示气候报告中的高阶因果结构，包括隐含和嵌套因果关系，用于提升因果推理和可读性量化。

摘要：

理解气候变化需要在复杂的因果网络中进行推理。然而，现有因果发现数据集主要捕捉显式、直接的因果关系。我们引入ClimateCause，一个由专家手动标注的高阶因果结构数据集，来自为政策服务的气候报告，包括隐含和嵌套因果性。因果-效应表达式被标准化并分解为个体因果关系以促进图构建，具有独特的因果-效应相关性、关系类型和时空上下文注释。我们进一步展示了ClimateCause在基于陈述语义复杂度的可读性量化中的价值。最后，基于大型语言模型在相关性推断和因果链推理上的基准测试，突显后者作为关键挑战。

英文摘要：

Understanding climate change requires reasoning over complex causal networks. Yet, existing causal discovery datasets predominantly capture explicit, direct causal relations. We introduce ClimateCause, a manually expert-annotated dataset of higher-order causal structures from science-for-policy climate reports, including implicit and nested causality. Cause-effect expressions are normalized and disentangled into individual causal relations to facilitate graph construction, with unique annotations for cause-effect correlation, relation type, and spatiotemporal context. We further demonstrate ClimateCause's value for quantifying readability based on the semantic complexity of causal graphs underlying a statement. Finally, large language model benchmarking on correlation inference and causal chain reasoning highlights the latter as a key challenge.

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。

↑