PrivacyAkinator: Articulating Key Privacy Design Decisions by Answering LLM-Generated Multiple-choice Questions
Not on the map. Why?
Abstract (arXiv)
NIST's Privacy Risk Assessment Methodology (PRAM) provides a structured framework for privacy experts to assess privacy risks. However, its complexity and reliance on expert knowledge make it difficult for novice developers to use effectively. This paper explores methods to lower these barriers. We first performed an observational study with 12 participants using PRAM in real-world scenarios, and found that novice developers struggled most with articulating privacy-related design decisions. We then developed PrivacyAkinator, an interactive tool that helps developers articulate key privacy decisions by answering LLM-generated multiple-choice questions. PrivacyAkinator introduces three innovations: a universal privacy representation that abstracts privacy-related design decisions into data flows and stakeholder interactions; a domain-aware design space mined from 10K privacy-related news articles; and a dynamic question-generation workflow to prioritize relevant questions. Our user study with 24 participants suggests that developers using PrivacyAkinator identified 47% more key decisions in 73% less time compared to PRAM.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 114 references that are in the map. First posted on arXiv 8 Apr 2026.
Builds on
23 of 114 references.
References · 23
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2023A Survey on Evaluation of Large Language Modelscited by 1,242
- 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
- 2019Question Answering for Privacy Policies: Combining Computational and Legal Perspectivescited by 67
- 2018Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learningcited by 50
- 2024CLEAR: Towards Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation for Large Language Model Applicationscited by 33
- 2024Using LLMs in Software Requirements Specifications: An Empirical Evaluationcited by 20
- 2022Goodbye Tracking? Impact of iOS App Tracking Transparency and Privacy Labelscited by 9
- 2024Empowering Users in Digital Privacy Management through Interactive LLM-Based Agentscited by 9
- 2016Augur: Mining Human Behaviors from Fiction to Power Interactive Systemscited by 5
- 2025"You don't need a university degree to comprehend data protection this way": LLM-Powered Interactive Privacy Policy Assessmentcited by 5
- 2023Understanding How to Inform Blind and Low-Vision Users about Data Privacy through Privacy Question Answering Assistantscited by 3
11 more
- 2018Why developers cannot embed privacy into software systems? An empirical investigationcited by 2
- 2021I'm all Ears! Listening to Software Developers on Putting GDPR Principles into Software Development Practicecited by 2
- 2022"We are a startup to the core": A qualitative interview study on the security and privacy development practices in Turkish software startupscited by 2
- 2024Matcha: An IDE Plugin for Creating Accurate Privacy Nutrition Labelscited by 2
- 2024Privacy Impact Assessments in the Wild: A Scoping Reviewcited by 2
- 2023Technocracy, pseudoscience and performative compliance: the risks of privacy risk assessments. Lessons from NIST's Privacy Risk Assessment Methodologycited by 1
- 2024Automated Detection and Analysis of Data Practices Using A Real-World Corpuscited by 1
- 2025Analysis of LLMs vs Human Experts in Requirements Engineeringcited by 1
- 2025Teaching Data Science Students to Sketch Privacy Designs through Heuristics (Extended Technical Report)cited by 1
- 2025SoK: Enhancing Privacy-Preserving Software Development from a Developers' Perspectivecited by 1
- 2025Zero Data Retention in LLM-based Enterprise AI Assistants: A Comparative Study of Market Leading Agentic AI Productscited by 1
Built on by
Not cited yet.