Klaudia Bałazy — accepted AI-conference papers

2026

Detecting Data Contamination in LLMs via In-Context Learning

Michał Zawalski, Meriem Boubdir, Klaudia Bałazy, Besmira Nushi, Pablo Ribalta

ICLR 2026poster

We present Contamination Detection via Context (CoDeC), a practical and accurate method to detect and quantify training data contamination in large language models. CoDeC distinguishes between data memorized during training and data outside the training distribution by measuring how in-context learn…

Cited by 0 Source ↗Scholar ↗

2021

Zero Time Waste: Recycling Predictions in Early Exit Neural Networks

Maciej Wolczyk, Bartosz Wójcik, Klaudia Bałazy, Igor T. Podolak, Jacek Tabor, Marek Śmieja +1

NeurIPS 2021poster

The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications. Early exit methods strive towards this goal by attaching additional Internal Classifiers (ICs) to intermediate layers of a neural network. ICs can quickly return predicti…

Cited by 50 Source ↗PDF ↗code ↗Scholar ↗