arXiv cs.CL· Emily Chen, Michelle Menachery, Himanshu Kumar, Rahul Nenavath, Amirfarrokh Iranitalab·· 13 小时前AI 评分24
UCVE：用图结构检索做合规校验
UCVE: Graph Structured Retrieval for Compliance Validation
AI 导读
UCVE 是一个领域无关的合规校验框架，将合规需求空间表示为合规需求图（CRG），并通过在强化学习加权拉普拉斯矩阵上做谱重排序完成检索。需求节点间的边由强化学习习得，奖励基于违规检测的遍历信号，使低通谱滤波能区分相关与不相关的义务簇。在三个合规领域上，UCVE 相比扁平余弦检索平均提升 4.3% matched-K 召回率，并持续优于强检索与图基线。
正文 · 原文
Abstract:Structured compliance validation requires determining whether every obligation in a predefined requirement space is satisfied, violated, or unaddressed by a given document. This can be described as a coverage problem that existing retrieval and classification systems, by treating requirements as independent, are not designed to solve. We introduce \textbf{\ac{UCVE}}, a domain-agnostic framework that represents compliance requirement spaces as a \ac{CRG} and performs retrieval via spectral reranking over its reinforcement learning-weighted Laplacian. Edges between requirement nodes are learned via reinforcement learning with a traversal reward grounded in violation detection, reshaping the graph's community structure such that low-pass spectral filtering distinguishes relevant from irrelevant obligation clusters. Evaluating across three compliance domains, \ac{UCVE} averages 4.3\% matched-$K$ recall lift over flat cosine retrieval and consistently outperforms strong retrieval and graph-based baselines.
| Comments: | Accepted to the Natural Legal Language Processing Workshop (NLLP 2026) at EMNLP 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.37323 [cs.CL] |
| (or arXiv:2610.37323v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37323 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Emily Chen [view email]
[v1]
Tue, 27 Oct 2026 14:35:00 UTC (2,055 KB)
来源：arXiv cs.CL · arxiv.org