一句话：提出结合条件感知元组、领域本体与 LLM 的 PoliCond 框架，将隐私政策矛盾检测 F1 从 58.2% 提升至 88.6%。
隐私政策虽用于披露数据实践，却常含内部冲突，损害透明度与用户信任。已有自动化矛盾分析依赖语言模型、元组式知识表示与本体（知识图谱）来消解自然语言歧义，但传统 (实体, 动作, 数据类型) 三元组缺乏上下文信息，无法区分不同场景下的数据收集行为，导致矛盾检测不完整甚至产生误导。为此，本文提出 PoliCond，将条件感知（condition-aware）元组表示、领域本体与大规模语言模型相结合，在表示中显式编码适用条件以区分场景。在已有基准上，PoliCond 取得 88.6% 的 F1，显著优于先前方法的 58.2%，平均每份政策处理时间为 8.4 秒；对 175 份真实隐私政策的分析发现 46 份存在不一致的政策，以及 48 对现有方法遗漏的矛盾片段，表明隐私政策不一致现象普遍，且 PoliCond 具备实际可用性。
Although privacy policies serve as the primary mechanism for disclosing data practices under regulations like the General Data Protection Regulation, they frequently contain internal conflicts that undermine transparency and user trust. Existing research has advanced automated privacy policy contradiction analysis by leveraging language models, tuple-based knowledge representations and ontologies (or knowledge graphs) to resolve natural language ambiguities. However, traditional 3-tuple (entity, action, data type) lack contextual information and fail to distinguish data collection practices under varying scenarios, leading to incomplete or misleading contradiction detection. To address these challenges, we present PoliCond, a framework that combines condition-aware tuple representations, domain ontologies and large language models. On established benchmarks, PoliCond achieves an F1 score of 88.6%, outperforming prior methods (58.2%), with an average processing time of 8.4 seconds per policy. In a real-world analysis of 175 privacy policies, PoliCond uncovers previously undetected internal contradictions, including 46 inconsistent policies and 48 contradictory pairs of policy segments missed by existing approaches. These findings underscore the prevalence of inconsistencies in privacy policies and demonstrate the practical utility of PoliCond.
DOI 原文 ·
@inproceedings{paperbot9196,
title = {PoliCond: Condition-Aware Ontology-Driven LLMs for Privacy Policy Contradiction Analysis},
author = {Yalin Feng and Yifei Lu and Minxue Pan},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00232}
}