Has collaborated with prominent researchers including Joana Bryson (Hertie School, Berlin), Verena Rieser (Google DeepMind), Oliver Lemon (Heriot-Watt University, Edinburgh), and Frank Rudzicz (Dalhousie University, Halifax).
Developed healthcare tools for clinical trials and senior care applications.
Programmed a humanoid robot that engages customers using advanced NLP techniques.
Co-organized the First Workshop on LLM Security (LLMSEC) at ACL 2025 (August 2025).
Co-organized the HEAL Workshop on Human-centered Evaluation and Auditing of Language Models at CHI 2025 (April 2025).
Organized the ML4CMH2024 Workshop on Machine Learning for Cognitive and Mental Health at AAAI 2024 (February 2024).
Background
Research interests include Natural Language Processing (NLP), Large Language Models (LLM), Trustworthy AI (TrustAI), Machine Learning for Healthcare (ML for Health), Evaluation and Metrics (Eval), Conversational AI (ConvAI), and Human-Robot Interaction (HRI).
Currently a Principal AI Scientist at Vanguard, specializing in artificial intelligence research with a focus on computational models of natural language processing.
Her work includes AI-powered natural language generation, machine learning applications for detecting cognitive impairment and mental health issues, and advancing human-robot interaction through AI systems.
Over a decade of experience in AI research across industry, academia, and non-profit sectors.
An advocate for open-source AI, contributing to major projects such as BLOOM LLM and BIG-Bench to promote reliable and accessible AI technologies.
Focused on ethical AI development and recognized as a respected voice in the field.