作为结构的时间：用于法律文件上可验证截止日期计算的时间依赖图
Time as Structure: Temporal Dependency Graphs for Verifiable Deadline Computation over Legal Documents
查看机构详情
- Leiden Institute of Advanced Computer Science (LIACS)（莱顿高级计算机科学研究所（LIACS））
- Leiden University（莱顿大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究针对法律文件截止日期计算问题，提出时间依赖图结合日历引擎的方法，在英国就业上诉法庭案件中表现优于语言模型，正确率达90.2%，可用于可验证的法律截止日期计算。
中文摘要 AI 辅助
错过提交截止日期一天，无论案件多有力，诉求都会被驳回。计算该截止日期极少简单：期限从触发事件开始，按法定惯例计算，可能因强制调解期而暂停。我们提出问题：语言模型应直接回答此类问题，还是读取文件后将算术运算交给代码。我们提取带时间的事实及其依赖关系，构建时间依赖图，并用日历正确的引擎从中计算截止日期。在英国就业上诉法庭判决上，该引擎重现了7项时效性裁决中的6项，且与法官确定的日期完全一致。4个语言模型中最强的那个，被要求回答相同案件时，算术运算正确但答案错误：在21次回复中有6次，其陈述的裁决与自身思路矛盾，且所有矛盾均表现为将逾期诉求判定为及时。为大规模测试系统，我们将解雇日期移至法定边界，生成427个答案由计算而非标注得出的案件。在两个系统均回答的案件中，该管道正确率为90.2%，而直接回答的正确率为61.2%。其局限在于提取：在合同案件中，错误几乎从未出现在算术上，而是出在选择期限应从哪个事件开始。
英文摘要
Miss a filing deadline by one day and the claim is barred, however strong the case. Computing that deadline is rarely simple: the period runs from a triggering event, is counted by a statutory convention, and may be suspended by a mandatory conciliation window. We ask whether a language model should answer such questions directly, or read the document and leave the arithmetic to code. We extract dated facts and their dependencies into a temporal dependency graph and compute deadlines from it with a calendar-correct engine. On UK Employment Appeal Tribunal judgments the engine reproduces six of seven timeliness rulings, and matches the judges' own dates to the day. The strongest of four language models, asked the same cases, gets the arithmetic right and the answer wrong: in six of twenty-one responses its stated verdict contradicts its own thinking, and every contradiction runs the same way, calling a late claim timely. To test the systems at scale we move the dismissal date across the statutory boundary, generating 427 cases whose answers are computed rather than annotated. On the cases both systems answer, the pipeline is right 90.2% of the time against 61.2% for direct answering. The limit is extraction: on contracts the errors are almost never in the arithmetic, but in choosing which event the period starts from.
