# PLACID: Privacy-preserving Large language models for Acronym Clinical Inference and Disambiguation

arXiv: https://arxiv.org/abs/2603.23678 · HTML: https://mlsanity.com/paper/2603.23678/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 57 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets](https://mlsanity.com/paper/1906.05474/) (2019)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [ExpertPrompting: Instructing Large Language Models to be Distinguished Experts](https://mlsanity.com/paper/2305.14688/) (2023)
- [Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves](https://mlsanity.com/paper/2311.04205/) (2023)
- [MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts](https://mlsanity.com/paper/1902.09476/) (2019)
- [Re-Reading Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2309.06275/) (2023)
- [Apple Intelligence Foundation Language Models: Tech Report 2025](https://mlsanity.com/paper/2507.13575/) (2025)
- [MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining](https://mlsanity.com/paper/2012.13978/) (2020)
- [GLADIS: A General and Large Acronym Disambiguation Benchmark](https://mlsanity.com/paper/2302.01860/) (2023)

## Abstract (arXiv)

Large Language Models (LLMs) offer transformative solutions across many domains, but healthcare integration is hindered by strict data privacy constraints. Clinical narratives are dense with ambiguous acronyms, misinterpretation these abbreviations can precipitate severe outcomes like life-threatening medication errors. While cloud-dependent LLMs excel at Acronym Disambiguation, transmitting Protected Health Information to external servers violates privacy frameworks. To bridge this gap, this study pioneers the evaluation of small-parameter models deployed entirely on-device to ensure privacy preservation. We introduce a privacy-preserving cascaded pipeline leveraging general-purpose local models to detect clinical acronyms, routing them to domain-specific biomedical models for context-relevant expansions. Results reveal that while general instruction-following models achieve high detection accuracy (~0.988), their expansion capabilities plummet (~0.655). Our cascaded approach utilizes domain-specific medical models to increase expansion accuracy to (~0.81). This novel work demonstrates that privacy-preserving, on-device (2B-10B) models deliver high-fidelity clinical acronym disambiguation support.