Frank Rudzicz

Using graph neural networks to objectively evaluate surgical performance.

A new method assesses the effectiveness of model editing in generating longer texts.

This article examines the dangers of harmful fine-tuning in language models.

A study introduces RepNoise to protect large language models from harmful fine-tuning.

New framework aims to boost ICD coding accuracy using electronic health records.

A study on storytelling differences between humans and AI-generated narratives.

Exploring Reverse Preference Attacks and their impact on model safety.

This article discusses the challenges of maintaining patient privacy and fairness in healthcare technology.