About this episode

Kyle Polich discusses the DPR framework with Fuyuan Lyu, exploring how it empowers users to control recommendations through natural language.

What if you could simply tell a recommendation system what you want instead of relying on likes, dislikes, and watch history? Kyle Polich talks with Fuyuan Lyu about the DPR framework, which combines large language models and traditional recommender systems to give users direct control over recommendations through natural language. Together they explore how conversational interfaces could transform platforms like YouTube, TikTok, and news feeds while preserving the strengths of modern recommendation algorithms.

People in this episode

Host: Kyle Polich

Guest: Fuyuan Lyu

Topics covered

• recommendation systems
• natural language processing
• conversational interfaces
• user control
• technology

Mentioned in this episode

Organizations: YouTube, TikTok

More episodes of Data Skeptic

• News Recommendations · July 2, 2026 · 46 min
• AutoLike · June 17, 2026 · 35 min

Explore listener stats, chart rankings, contacts and more on the Data Skeptic podcast page.