发表机构
Texas A&M University（德克萨斯农工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究构建了用于提取施工事故因果信息的ConstructCIE数据集，评估了相关模型的性能，发现模型在精确跨度提取上存在局限，需强化领域基础与证据提取。
AI 中文摘要
施工事故叙述包含丰富的因果信息，但这些证据往往是隐含的、长跨度的且分散的。我们推出ConstructCIE，这是一个针对OSHA施工事故报告中因果信息提取的人工标注数据集。该数据集采用事故类型、因果因素、子因果因素及支撑证据跨度的分层模式。我们在端到端分层提取场景中评估了监督序列标记器和指令调优的LLM。结果显示，多数被评估模型在事故类型预测上表现出色，且能捕捉到广泛的因果含义，但在精确的跨度级提取上仍存在局限。JHE通常在精确匹配和软匹配上表现更强，而IHE有时能取得更高的关键词F1值。错误分布因提取策略而异，但证据选择和跨度边界错误仍很常见。这些发现表明，针对施工事故的可靠因果信息提取需要更强的领域基础和更准确的证据提取。
英文摘要
Construction accident narratives contain rich causal information, but the evidence is often implicit, long-span, and distributed. We introduce ConstructCIE, a manually annotated dataset for Causal Information Extraction from OSHA construction accident reports. The dataset uses a hierarchical schema for accident types, causal factors, sub-causal factors, and supporting evidence spans. We evaluate supervised sequence taggers and instruction-tuned LLMs in an end-to-end hierarchical extraction setting. Results show that most evaluated models achieve strong accident-type prediction and recover broad causal meaning but remain limited in precise span-level extraction. Joint Hierarchical Extraction generally achieves stronger exact and soft matching, while Individual Hierarchical Extraction sometimes achieves higher keyword F1. Error distributions vary by extraction strategy, but evidence-selection and span-boundary errors remain common. These findings show that reliable Causal Information Extraction for construction accidents requires stronger domain grounding and more accurate evidence extraction. The code and data can be found at https://github.com/lab-flair/ConstructCIE .
CommentsPaper accepted by EMNLP 2026 Findings
