Demystifying Legalese: An Automated Approach for Summarizing and Analyzing Overlaps in Privacy Policies and Terms of Service
This work addresses the issue of uninformed data sharing for users by making legal documents more accessible, though it is incremental as it applies existing models to a specific domain.
The paper tackled the problem of complex legalese in privacy policies and terms of service by developing automated language models to summarize and analyze these documents, achieving a 0.74 F1-score with RoBERTa and identifying overlaps that highlight GDPR compliance issues.
The complexities of legalese in terms and policy documents can bind individuals to contracts they do not fully comprehend, potentially leading to uninformed data sharing. Our work seeks to alleviate this issue by developing language models that provide automated, accessible summaries and scores for such documents, aiming to enhance user understanding and facilitate informed decisions. We compared transformer-based and conventional models during training on our dataset, and RoBERTa performed better overall with a remarkable 0.74 F1-score. Leveraging our best-performing model, RoBERTa, we highlighted redundancies and potential guideline violations by identifying overlaps in GDPR-required documents, underscoring the necessity for stricter GDPR compliance.