The open-world deployment of Machine Learning (ML) algorithms in safety-critical
applications such as autonomous vehicles needs to address a variety of ML vulnerabilities …

Abstract Generative Pre-trained Transformer (GPT) models have exhibited exciting progress
in their capabilities, capturing the interest of practitioners and the public alike. Yet, while the …

Despite efforts to align large language models (LLMs) with human intentions, widely-used
LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an …

A common approach to transfer learning under distribution shift is to fine-tune the last few
layers of a pre-trained model, preserving learned features while also adapting to the new …

Background Medical text, as part of an electronic health record, is an essential information
source in healthcare. Although natural language processing (NLP) techniques for medical …

The goal of data attribution is to trace model predictions back to training data. Despite a long
line of work towards this goal, existing approaches to data attribution tend to force users to …

For machine learning systems to be reliable, we must understand their performance in
unseen, out-of-distribution environments. In this paper, we empirically show that out-of …

Gabriel Goh: Research lead. Gabriel Goh first discovered multimodal neurons, sketched out
the project direction and paper outline, and did much of the conceptual and engineering …

Deep neural networks often rely on spurious correlations to make predictions, which hinders
generalization beyond training environments. For instance, models that associate cats with …

Machine learning models often perform poorly on subgroups that are underrepresented in
the training data. Yet, little is understood on the variation in mechanisms that cause …