# PolicyLR: A Logic Representation For Privacy Policies

arXiv: https://arxiv.org/abs/2408.14830 · HTML: https://mlsanity.com/paper/2408.14830/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 57 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [Poisoning Retrieval Corpora by Injecting Adversarial Passages](https://mlsanity.com/paper/2310.19156/) (2023)
- [Entailment as Few-Shot Learner](https://mlsanity.com/paper/2104.14690/) (2021)
- [AnglE-optimized Text Embeddings](https://mlsanity.com/paper/2309.12871/) (2023)
- [Question Answering for Privacy Policies: Combining Computational and Legal Perspectives](https://mlsanity.com/paper/1911.00841/) (2019)
- [PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails](https://mlsanity.com/paper/2402.15911/) (2024)
- [Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning](https://mlsanity.com/paper/1802.02561/) (2018)
- [Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation](https://mlsanity.com/paper/2405.20485/) (2024)
- [Privacy Policies over Time: Curation and Analysis of a Million-Document Dataset](https://mlsanity.com/paper/2008.09159/) (2020)
- [The Privacy Policy Landscape After the GDPR](https://mlsanity.com/paper/1809.08396/) (2018)
- [Large Language Models: A New Approach for Privacy Policy Analysis at Scale](https://mlsanity.com/paper/2405.20900/) (2024)
- [PoliGraph: Automated Privacy Policy Analysis using Knowledge Graphs (Journal Version)](https://mlsanity.com/paper/2210.06746/) (2022)
- [ATLAS: Automatically Detecting Discrepancies Between Privacy Policies and Privacy Labels](https://mlsanity.com/paper/2306.09247/) (2023)
- [Analyzing Privacy Policies Using Contextual Integrity Annotations](https://mlsanity.com/paper/1809.02236/) (2018)
- [Privacy Policies Across the Ages: Content and Readability of Privacy Policies 1996--2021](https://mlsanity.com/paper/2201.08739/) (2022)
- [Compliance Checking with NLI: Privacy Policies vs. Regulations](https://mlsanity.com/paper/2204.01845/) (2022)
- [The Overview of Privacy Labels and their Compatibility with Privacy Policies](https://mlsanity.com/paper/2303.08213/) (2023)

## Built on by (most cited first, 3 of 3)

- [Auto-SPT: Automating Semantic Preserving Transformations for Code](https://mlsanity.com/paper/2512.06042/) (2025)
- [Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code](https://mlsanity.com/paper/2609.19199/) (2026)
- [Privacy Washing: Detecting Internal Contradictions in Privacy Policies](https://mlsanity.com/paper/2609.02055/) (2026)

## Abstract (arXiv)

Privacy policies are crucial in the online ecosystem, defining how services handle user data and adhere to regulations such as GDPR and CCPA. However, their complexity and frequent updates often make them difficult for stakeholders to understand and analyze. Current automated analysis methods, which utilize natural language processing, have limitations. They typically focus on individual tasks and fail to capture the full context of the policies. We propose PolicyLR, a new paradigm that offers a comprehensive machine-readable representation of privacy policies, serving as an all-in-one solution for multiple downstream tasks. PolicyLR converts privacy policies into a machine-readable format using valuations of atomic formulae, allowing for formal definitions of tasks like compliance and consistency. We have developed a compiler that transforms unstructured policy text into this format using off-the-shelf Large Language Models (LLMs). This compiler breaks down the transformation task into a two-stage translation and entailment procedure. This procedure considers the full context of the privacy policy to infer a complex formula, where each formula consists of simpler atomic formulae. The advantage of this model is that PolicyLR is interpretable by design and grounded in segments of the privacy policy. We evaluated the compiler using ToS;DR, a community-annotated privacy policy entailment dataset. Utilizing open-source LLMs, our compiler achieves precision and recall values of 0.91 and 0.88, respectively. Finally, we demonstrate the utility of PolicyLR in three privacy tasks: Policy Compliance, Inconsistency Detection, and Privacy Comparison Shopping.