Large Language Models (LLMs) have demonstrated impressive capabilities for natural language understanding and generation. What if we power recommender systems with LLMs that can reason through user activities on the platform, and can help plan recommendations accordingly? Equipped with UXR insights that people use nuanced language to describe their long-term interest journeys, and they want more user agency in their recommender platforms, we pinpoint a combination of LLMs and personalization as a key ingredient for the next generation of assistive recommendation.

In this talk, we will introduce a novel LLM-based journey service that allows to uncover the personalized nuanced user interests, needs and goals of users, i.e., their interest journeys, through fine-tuning and prompt-tuning LLMs. We will discuss research findings from this work on LLMs for better user understanding, and will provide insights on LLM-based long-term planning to assist user journeys. Finally, we will provide challenges and opportunities across our long quest of integrating LLMs into user facing products to transform the user experience.