Overview
Download the presentation slides
Today in our AI/ML seminar, we were pleased to have Maliha Zahan Chowdhury as the presenter. Maliha is a first-year PhD student in Dr. Zhishuai Guo’s research group.
Her talk focused on Direct Preference Optimization (DPO), primarily based on the original 2023 DPO paper. Although the paper was published only three years ago, it has already been cited nearly 8,000 times, reflecting its significant impact on LLM alignment and optimization research.
In her presentation, Maliha provided a detailed introduction to the core principles of DPO, including the key mathematical formulations behind the method. She also discussed its limitations and potential directions for future work.
During the discussion session, seminar participants engaged in a thoughtful conversation about the different use cases of various LLM optimization algorithms, as well as their differing data requirements and practical considerations.
Thank you, Maliha, for an excellent and well-structured presentation!