Kathleen C. Fraser

Associate Professor · School of Electrical Engineering and Computer Science · University of Ottawa

NLP AI safety bias & fairness model evaluation NLP for health

My research is in natural language processing and artificial intelligence with a focus on ethical AI and AI safety, including bias and fairness, social stereotypes, deception, manipulation, and model evaluation. A large part of my work also applies NLP to healthcare, detecting early signs of cognitive impairment from speech and language.

news

We will be presenting a tutorial at FAccT 2026 in Montreal, on counterfactual fairness in vision-language models. Register now
As of September 1 2025, I have started a new position at the University of Ottawa. Many fond farewells to my team at the NRC.
Our paper on detecting AI text on social media (ACL Findings 2025).
New work with Intel Labs on bias in large vision-language models at NAACL 2025.
Our survey on detecting AI-generated text is published in the Journal of Artificial Intelligence Research.
Nature news featuring our work: AI image generators often give racist and sexist results: can they be fixed?

current projects

What I’m working on

Feel free to get in touch for more information or possible collaboration.

Cognitive Decline

Algorithms to automatically detect speech and language markers of cognitive or mental state.

Stereotyping & Bias

Examining stereotyping and bias in social media text and in machine learning models.

AI Safety

Evaluating frontier and fine-tuned models for safety risks, and designing mitigations.

selected publications

Selected publications

For an up-to-date list, please see my Google Scholar page.

Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods

Fraser, Dawkins, & Kiritchenko · 2025

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency

Fraser, Dawkins, Nejadgholi, & Kiritchenko · 2025

Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals

Howard, Fraser, Bhiwandiwalla, & Kiritchenko · 2024

Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images

Fraser & Kiritchenko · 2024

Aporophobia: An Overlooked Type of Toxic Language Targeting the Poor

Kiritchenko, Curto, Nejadgholi, & Fraser · 2023

A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?

Fraser, Nejadgholi, & Kiritchenko · 2023

Computational Modeling of Stereotype Content in Text

Fraser, Kiritchenko, & Nejadgholi · 2022

Does Moral Code Have a Moral Code? Probing Delphi’s Moral Philosophy

Fraser, Kiritchenko, & Balkir · 2022

Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection

Balkir, Nejadgholi, Fraser, & Kiritchenko · 2022

Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective

Kiritchenko, Nejadgholi, & Fraser · 2021

Measuring Cognitive Status from Speech in a Smart Home Environment

Fraser & Komeili · 2021

Predicting MCI Status From Multimodal Language Data Using Cascaded Classifiers

Fraser, Lundholm Fors, Eckerström, Öhman, & Kokkinakis · 2019

How Do We Feel When a Robot Dies? Emotions Expressed on Twitter Before and After hitchBOT’s Destruction

Fraser, Zeller, Smith, Mohammad, & Rudzicz · 2019

Multilingual Prediction of Alzheimer’s Disease Through Domain Adaptation and Concept-Based Language Modelling

Fraser et al. · 2019

An Analysis of Eye-Movements During Reading for the Detection of Mild Cognitive Impairment

Fraser, Lundholm Fors, Kokkinakis, & Nordlund · 2017

about

Academic bio

Dr. Kathleen Fraser is an Associate Professor in the School of Electrical Engineering and Computer Science at the University of Ottawa, where she investigates language technologies for healthcare and social good. Her recent research has focused on social and ethical issues in natural language processing, such as identifying stereotypes and implicitly abusive language in social media text, as well as improving the interpretability and transparency of machine learning models. She is also active in developing methods to help detect early signs of cognitive decline from speech patterns and eye movements.

Previously, Dr. Fraser worked as a Research Officer at the National Research Council of Canada. She received her PhD in Computer Science from the University of Toronto in 2016, under the supervision of Graeme Hirst and Jed Meltzer, and was awarded the Governor General’s Gold Academic Medal.

contact