Hila Gonen
About
Appointed Canada CIFAR AI Chair – 2026
Hila’s research interests lie at the intersection of natural language processing (NLP, machine learning and AI. Her long-term vision is transforming large language models (LLMs) into responsible, reliable and trustworthy systems, which are available and fair across languages and different socio-demographic groups. In her research, she focuses on three main threads: (1) Control and interpretation of models: understanding model behavior and controlling model generation; (2) Reliability, safety and fairness: making models more consistent and safe, and mitigating biases and risks; (3) Multilinguality: creating NLP tools that equitably serve speakers of as many languages as possible, as well as understanding the emergent property of cross-linguality in models. Additionally, she has recently developed an interest in employing NLP tools and methodologies in the health domain.
Awards
- Women’s Postdoctoral Career Development Award in Science, Weitzmann Institute of Science, 2023
- Best Doctoral Dissertation Award Runner Up, Israeli Association for Artificial Intelligence (IAAI), 2022
- EECS Rising Stars Award, UT Austin, 2022
- Rothschild Postdoctoral Fellowship, Yad Hanadiv, 2021
- Best paper award, CoNLL (Conference on Computational Natural Language Learning), 2019
Relevant Publications
- Zadok, M., Peled-Cohen, L., Calderon, N., Gonen, H., Schnaider Beeri, M., & Reichart, R. (2026). “Human and LLM judgments of cognitive impairment from language: An explainable AI approach”. Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring.
- Verma, S., Hines, K., Bilmes, J., Siska, C., Zettlemoyer, L., Gonen, H., & Singh, C. (2025). “OMNIGUARD: An efficient approach for AI safety moderation across languages and modalities”. Proceedings of EMNLP.
- Gonen, H., Iyer, S., Blevins, T., Smith, N. A., & Zettlemoyer, L. (2023). “Demystifying prompts in language models via perplexity estimation”. Findings of EMNLP.
- Ahia, O., Kumar, S., Gonen, H., Kasai, J., Mortensen, D. R., Smith, N. A., & Tsvetkov, Y. (2023).” Do all languages cost the same? Tokenization in the era of commercial language models”. Proceedings of EMNLP.
- Gonen, H., & Goldberg, Y. (2019). “Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them”. Proceedings of NAACL.