Skip to main content

Niki Howe

PhD Candidate | Mila, Université de Montréal

Niki Howe is a PhD candidate at Mila and the Université de Montréal, where they also received their MSc. They hold BAs in Math and CS from Williams College and the University of Cambridge, respectively. At FAR.AI, Niki is exploring how scale affects the robustness of LLMs.

Publications

Exploring Scaling Trends in LLM Robustness

Robustness

While larger language models exhibit impressive capabilities, they remain vulnerable to adversarial prompts. Empirical findings show that robustness against such attacks significantly improves with adversarial training, but not with model scaling alone.

July 25, 2024
Date Range

News

Does Robustness Improve with Scale?

Robustness & Security

Frontier LLMs like ChatGPT are powerful but not always robust. Scale helps with many things. We wanted to see if scaling up the model size can ‘solve’ robustness issues.

July 22, 2024
Date Range

Research

Our research explores a portfolio of high-potential agendas.

Events

Our events bring together global leaders in AI.

Programs

Our programs build the field of trustworthy and secure AI