发表机构
Johns Hopkins University; University of Maryland School of Law（约翰斯·霍普金斯大学; 马里兰大学法学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本工作构建了首个专家标注的树状法律论证语料库（42篇美国联邦税务意见），提出五类功能标签及支持树结构，实验表明功能标签可学习且监督微调提升案件内检索，但跨案件泛化仍弱。
AI 中文摘要
法律论证挖掘支持段落分类、检索和论证补全。本工作引入了一个由专家标注的数据集，包含42篇关于《国内税收法》第368条下公司重组的美国联邦税务意见书。据我们所知，这是该领域首个由专家标注的树状结构论证语料库。明确的文本跨度被赋予五种功能标签之一：规则、分析、结论、背景事实和程序历史。规则、分析和结论跨度可以链接成有向支持树，而背景事实和程序历史则发挥上下文功能。该语料库提供基于跨度、基于句子、平面和树状结构的表示。一致性分析表明，功能节点标签比有向支持边和隐式中间结论更可靠。有向路径一致性优于直接边一致性，这表明广泛的可达性比精确的局部分解更稳定。分类实验表明，在案件分离评估下，功能标签是可学习的。检索实验表明，监督微调改善了案件内检索。然而，跨案件泛化仍然较弱。该数据集支持法律段落分类，并为美国联邦税务判例法中的结构化论证挖掘提供了一个保守的基准。
英文摘要
Legal argument mining supports passage classification, retrieval, and argument completion. This work introduces an expert-annotated dataset of 42 U.S. federal tax opinions on corporate reorganizations under I.R.C. §368. To our knowledge, it is the first expert-annotated, tree-structured argument corpus for this domain. Explicit spans receive one of five functional labels: Rule, Analysis, Conclusion, Background Facts, and Procedural History. Rule, Analysis, and Conclusion spans can be linked into directed support trees, while Background Facts and Procedural History serve a contextual function. The corpus provides span-based, sentence-based, flat, and tree-structured representations. Agreement analysis shows that functional node labels are more reliable than directed support edges and implicit intermediate conclusions. Directed-path agreement is stronger than direct-edge agreement, which indicates that broad reachability is more stable than exact local decomposition. Classification experiments show that functional labels are learnable under case-disjoint evaluation. Retrieval experiments show that supervised fine-tuning improves within-case retrieval. However, cross-case generalization remains weak. The dataset supports legal passage classification and provides a conservative benchmark for structured argument mining in U.S. federal tax case law.
Comments28 pages, 4 figures
