Portrait of Jean-François Godbout

Jean-François Godbout

Associate Academic Member
Full Professor, Université de Montréal
Research Topics
AI Safety
Disinformation
Generative Models
Google Scholar
LinkedIn

Biography

Jean-François Godbout is a professor at the Université de Montréal in the Department of Political Science and an Associate Academic Member at Mila - Quebec Artificial Intelligence Institute. His research is primarily focused on computational social science, AI safety, and the impact of generative AI on society. He is currently Director of the Data analysis undergraduate program in social sciences and humanities at the Université de Montréal and a researcher at IVADO.

Current Students

Andreea Musulan
Postdoctorate - Université de Montréal
Camille Thibault
Master's Research - Université de Montréal
Co-supervisor :
Reihaneh Rabbany
Website
Github
Google Scholar
Sveta Zhuk
Master's Research - Université de Montréal
Co-supervisor :
Reihaneh Rabbany

Publications

Comparing GPT-4 and Open-Source Language Models in Misinformation Mitigation
Tyler Vergho
Jean-François Godbout
Reihaneh Rabbany
Kellin Pelrine
Recent large language models (LLMs) have been shown to be effective for misinformation detection. However, the choice of LLMs for experiment… (see more)s varies widely, leading to uncertain conclusions. In particular, GPT-4 is known to be strong in this domain, but it is closed source, potentially expensive, and can show instability between different versions. Meanwhile, alternative LLMs have given mixed results. In this work, we show that Zephyr-7b presents a consistently viable alternative, overcoming key limitations of commonly used approaches like Llama-2 and GPT-3.5. This provides the research community with a solid open-source option and shows open-source models are gradually catching up on this task. We then highlight how GPT-3.5 exhibits unstable performance, such that this very widely used model could provide misleading results in misinformation detection. Finally, we validate new tools including approaches to structured output and the latest version of GPT-4 (Turbo), showing they do not compromise performance, thus unlocking them for future research and potentially enabling more complex pipelines for misinformation mitigation.
2024-01-12
ArXiv (preprint)
doi.org
arxiv.org