cv

Master of Science

Massachusetts Institute of Technology

Center for Constructive Communication

Bachelor of Arts

McGill University

Honours Math and Computer Science

On the Relationship between Truth and Political Bias in Language Models

Empirical Methods in Natural Language Processing (EMNLP)

LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users

Safe Generative AI Workshop @ NeurIPS 2024

Are Diffusion Models Vision-And-Language Reasoners?

Advances in Neural Information Processing Systems (NeurIPS)

An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models

Association for Computational Linguistics

Research Assistant

MIT Center for Constructive Communication

Data Science Intern

Unity

Worked on the Ad Unit Innovation team and conducted feature engineering and hyperparameter tuning experiments on the bid throttling model.

• Decreased model training time by 25% and reduced model size and number of parameters by 50%.
• Began an initiative to incorporate app store game reviews as a new feature to the Ad Revenue model.
• Cleaned and explored data, built a neural network for sentiment analysis, and calculated the vector space embedding of each game.
• Created a data pipeline to do all of the preprocessing and vectorization in GCP Dataflow to speed up the process as well as make it more flexible and more easily reused.

Undergraduate Student Researcher

McGill University

Built probabilistic models for identifying the “geo-indicativeness” of text using novel machine learning techniques applied to big, public, geosocial datasets.

• Models used to create an educational resource, LocatEd, for increasing location privacy awareness among Canadian youth.
• Supervised by Dr. Grant McKenzie.

Honours Algorithms and Data Structures Course Assistant

McGill University

• Held weekly office hours for students in the course to answer their questions and help with assignments.
• Developed solutions for and graded assignments and exams.

Student Researcher

Shamoon College of Engineering

Machine learning (NLP) research project to predict author gender given a text with the goal of performing a case study on female authors who wrote books under male pseudonyms.

• Preprocessed and cleaned data using Stanford CoreNLP and scikit-learn.
• Designed and implemented baseline experiments using SVMs.
• Project supervised by Dr. Irina Rabaev and Dr. Marina Litvak.

Undergraduate Student Researcher

Mila Quebec AI Institute

• Evaluated gender debiasing techniques on pre-trained language models using NLP (paper accepted to ACL'22).
• Investigated the effect of gender debiasing on fine-tuned language models such as BERT using PyTorch.
• Explored debiasing methods and reformulated bias metrics for racial and religious biases.

Reviewer for ACL Rolling Review (ARR) December

Reviewer for ACL Rolling Review (ARR) October

Natural Sciences and Engineering Research Council of Canada (NSERC)

$17,500

Mila Quebec AI Institute

$5,000

McGill University

Top 10% of students by GPA.

McGill University

$9,000

Bronx High School of Science

Awarded to top students for outstanding academic achievement and leadership and service to the school.

NY Cardiac Center Scholarship

$20,000. Awarded to top 3 GPA in graduating class of 750 students.

National Merit Scholarship Corporation