# Privacy Meets Explainability: Managing Confidential Data and Transparency Policies in LLM-Empowered Science

arXiv: https://arxiv.org/abs/2504.09961 · HTML: https://mlsanity.com/paper/2504.09961/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 54 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap](https://mlsanity.com/paper/2306.01941/) (2023)
- ["It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents](https://mlsanity.com/paper/2309.11653/) (2023)
- [BERN2: an advanced neural biomedical named entity recognition and normalization tool](https://mlsanity.com/paper/2201.02080/) (2022)
- [Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection](https://mlsanity.com/paper/2309.03057/) (2023)
- [HunFlair: An Easy-to-Use Tool for State-of-the-Art Biomedical Named Entity Recognition](https://mlsanity.com/paper/2008.07347/) (2020)
- [Can LLMs get help from other LLMs without revealing private information?](https://mlsanity.com/paper/2404.01041/) (2024)
- [HunFlair2 in a cross-corpus evaluation of biomedical named entity recognition and normalization tools](https://mlsanity.com/paper/2402.12372/) (2024)
- [TILT: A GDPR-Aligned Transparency Information Language and Toolkit for Practical Privacy Engineering](https://mlsanity.com/paper/2012.10431/) (2020)
- [OVRseen: Auditing Network Traffic and Privacy Policies in Oculus VR](https://mlsanity.com/paper/2106.05407/) (2021)
- [Towards Explainable and Language-Agnostic LLMs: Symbolic Reverse Engineering of Language at Scale](https://mlsanity.com/paper/2306.00017/) (2023)
- [Toward the Cure of Privacy Policy Reading Phobia: Automated Generation of Privacy Nutrition Labels From Privacy Policies](https://mlsanity.com/paper/2306.10923/) (2023)

## Built on by (most cited first, 1 of 1)

- [AInterviewer: A Platform for Designing and Conducting AI-led Qualitative Interviews](https://mlsanity.com/paper/2606.20588/) (2026)

## Abstract (arXiv)

As Large Language Models (LLMs) become integral to scientific workflows, concerns over the confidentiality and ethical handling of confidential data have emerged. This paper explores data exposure risks through LLM-powered scientific tools, which can inadvertently leak confidential information, including intellectual property and proprietary data, from scientists' perspectives. We propose "DataShield", a framework designed to detect confidential data leaks, summarize privacy policies, and visualize data flow, ensuring alignment with organizational policies and procedures. Our approach aims to inform scientists about data handling practices, enabling them to make informed decisions and protect sensitive information. Ongoing user studies with scientists are underway to evaluate the framework's usability, trustworthiness, and effectiveness in tackling real-world privacy challenges.