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: LexFlip: A Dissociation Diagnostic for Legal Meaning Preservation Metrics
arXiv:2609.05296v1 介绍 LexFlip，用 373 个魁北克法语法规最小扰动样本构造解离测试：在保留 0.93 相同词元的同时反转法律效力，并统一评测指标、回归模型与提示裁判。七种 embedding 与 BERTScore 指标在该类编辑上仅消耗相同到无关区间的 0.022 至 0.039，而双向 NLI 为 0.670；FrJudge 上人类上限为 r=0.597，裸长度特征却超过所有语义指标且优势最小。
展示来源全文，完整内容以原文页面为准。
arXiv:2609.05296v1 Announce Type: new Abstract: Does a simplified legal clause still say what the original said? The checks in current use cannot establish that it does: requiring an identical pair to score highest and an unrelated pair lowest moves lexical overlap and legal force together, so any monotone function of token overlap satisfies both. Our remedy is a dissociation, an item holding surface form fixed while legal force moves. We release LexFlip, 373 minimal perturbations of Quebec statutory French that reverse legal force while preserving 0.93 of the tokens, with a harness scoring metrics, regressors and prompted judges alike. The seven embedding and BERTScore metrics we test spend only 0.022 to 0.039 of their identical-to-unrelated range on such an edit, against 0.670 for bidirectional NLI, the one family the identical-pair check would disqualify. On FrJudge, against a measured human ceiling of r=0.597, a bare length feature outscores every semantic metric and has the lowest margin we measure.
现有法律文本简化“保义”评测可能把表层词重叠误当法律效力不变，从而高估自动化评估与生成式改写的可靠性。
文书与研报规范引注
《LexFlip 检验法律释义保持指标》（来源: arXiv cs.CL，发布日期: 2026/09/14，访问链接: https://arxiv.org/abs/2609.05296）