The School of Computer Science at the University of Windsor is pleased to present …
Lusifer: LLM-based User Simulated Feedback Environment for Online Recommender Systems
PhD. Seminar by: Danial Ebrat
Date: Friday, August 1st, 2025
Time: 1:00 PM
Location: Essex Hall, Room 122
Reinforcement learning (RL) recommender systems often rely on static datasets that fail to capture the fluid, ever-changing nature of user preferences in real-world scenarios. Meanwhile, generative AI techniques have emerged as powerful tools for creating synthetic data, including user profiles and behaviours. Recognizing this potential, we introduce Lusifer, an LLM-based simulation environment designed to generate dynamic, realistic user feedback for online or RL-based recommender training. In Lusifer, user profiles are incrementally updated at each interaction step, with Large Language Models (LLMs) providing transparent explanations of how and why preferences evolve. By processing textual metadata—such as movie overviews and tags—Lusifer creates more context-aware user states and simulates feedback on new items, including those with limited or no prior ratings. This approach reduces reliance on extensive historical data and facilitates cold-start scenario handling and adaptation to out-of-distribution cases. Our experiments compare Lusifer with traditional collaborative filtering models, revealing that while Lusifer can be comparable in predictive accuracy, it excels at capturing dynamic user responses and yielding explainable results at every step. These qualities highlight its potential as a scalable, ethically sound alternative to live user experiments, supporting iterative and user-centric evaluations of RL-based recommender strategies.
Internal Reader: Dr. Hossein Fani
Internal Reader: Dr. Ikjot Saini
External Reader: Dr. Esraa Abdelhalim
Advisor (s): Dr. Luis Rueda
