法律 AI // 资讯总览
需要被持续追踪的
法律 AI 信号。
本期索引按监管、判例、实务与研究归档；可依主题或关键字定位已发布记录。
法律 AI // 资讯总览
本期索引按监管、判例、实务与研究归档；可依主题或关键字定位已发布记录。
原题: ImmigrationReason: A Structured Dataset of U.S. Immigration Appeals for Legal Reasoning Research
涉及法律行业大模型应用、律所与企业法务数智化实践指引。
arXiv论文arXiv:2608.20391v1介绍了ImmigrationReason，这是一个面向法律推理研究的美国移民行政裁决结构化数据集。数据集收录美国公民及移民服务局行政上诉办公室（USCIS AAO）2005年至2026年的12,375份非先例决定，记录适用法律框架、逐项标准的证据充分性判断、五类标签、裁决者逐字批评、全部引文及最终处理结果，并附经Claude转录的来源文本。研究团队采用结合两种独立模态和Opus 4.7比较提示裁决的三轮提取流程，并由法律领域专家抽查500份记录。数据集中包含近9,000条AAO认定法律错误的逐字实例，覆盖2016年Dhanasar规则变更前后的制度转型，可用于结果预测、裁决错误分析及高风险监管领域智能体研究。
展示来源全文，完整内容以原文页面为准。
arXiv:2608.20391v1 Announce Type: new Abstract: Most legal NLP resources draw from federal case law and focus on coarse classification, leaving administrative adjudication, where the vast majority of government decisions occur, essentially unaddressed. We introduce ImmigrationReason, a large-scale structured dataset derived from 12,375 non-precedent decisions of the U.S. Citizenship and Immigration Services (USCIS) Administrative Appeals Office (AAO) spanning 2005 to 2026. Each record captures the applicable legal framework, per-criterion evidence-sufficiency findings under a five-category label, verbatim adjudicator-criticism quotes, all citations, and final dispositions, alongside high-quality Claude-transcribed source text. Extraction quality is validated through a three-pass pipeline combining two independent modalities with comparison-prompt adjudication by Opus 4.7, and verified by domain experts on a 500-record sample. The dataset documents nearly 9,000 verbatim instances of AAO-identified legal errors, spans a natural legal-regime transition (the 2016 Dhanasar rule change), and covers 21 years of adjudication. We analyze the dataset in detail and outline research directions it enables, from outcome prediction and adjudicator-error analysis to agent design for high-stakes regulatory domains.
文书与研报规范引注
《ImmigrationReason发布美国移民上诉结构化数据集》（来源: arXiv cs.CL，发布日期: 2026/10/08，访问链接: https://arxiv.org/abs/2608.20391）