Nicolas Pielawski

AI Researcher in healthcare

Hi there! I’m a researcher working at the intersection of AI and healthcare, with a soft spot for Bayesian statistics, uncertainty quantification, information theory, and any problem that requires a bit of mathematical thinking to untangle.

Most of my work lives in the space where data meets decision-making — whether it’s building smarter systems for healthcare or thinking through how we can make AI more trustworthy and grounded in reality. I’m especially interested in modeling uncertainty, and I tend to get excited about anything that helps us understand why a model behaves the way it does.

Feel free to reach out if you want to chat about AI in general or in healthcare, or even if you want to convince me that “infinity” is a real concept. :)

selected publications

NLDL
Hallucination Detection in LLMs: Fast and Memory-Efficient Finetuned Models

Gabriel Y. Arteaga, Thomas B. Schön, and Nicolas Pielawski

In Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL), 07–09 jan 2025

Abs arXiv Bib HTML PDF Code

Uncertainty estimation is a necessary component when implementing AI in high-risk settings, such as autonomous cars, medicine, or insurances. Large Language Models (LLMs) have seen a surge in popularity in recent years, but they are subject to hallucinations, which may cause serious harm in high-risk settings. Despite their success, LLMs are expensive to train and run: they need a large amount of computations and memory, preventing the use of ensembling methods in practice. In this work, we present a novel method that allows for fast and memory-friendly training of LLM ensembles. We show that the resulting ensembles can detect hallucinations and are a viable approach in practice as only one GPU is needed for training and inference.
@inproceedings{hallucinationDetection2025, title = {Hallucination Detection in {LLM}s: Fast and Memory-Efficient Finetuned Models}, author = {Arteaga, Gabriel Y. and Sch{\"o}n, Thomas B. and Pielawski, Nicolas}, booktitle = {Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL)}, pages = {1--15}, year = {2025}, editor = {Lutchyn, Tetiana and Ramírez Rivera, Adín and Ricaud, Benjamin}, volume = {265}, series = {Proceedings of Machine Learning Research}, month = {07--09 Jan}, publisher = {PMLR}, url = {https://proceedings.mlr.press/v265/arteaga25a.html}, }