Music Playlist Captioning at Scale with Large Language Models
For music streaming services, this work demonstrates a scalable solution for generating natural language descriptions of playlists, leading to measurable engagement gains.
Deezer deployed an automatic playlist captioning system using LLMs to generate descriptive captions for personalized playlists, which improved user engagement for millions of Daily Mix users.
Music streaming services such as Deezer often recommend personalized playlists to users. Playlist captioning, which involves describing these playlists in natural language, is essential for helping users understand the content behind each recommendation, yet remains challenging at scale. This paper presents the automatic playlist captioning system deployed on Deezer in 2025 to address this challenge. Leveraging recent advances in large language models (LLMs) to generate descriptive captions from diverse data sources in a controlled manner, this system now powers the Daily Mix feature, used by millions of users. This deployment has led to significant improvements in user engagement, highlighting how the semantic framing of an unchanged recommendation shapes user perception in online personalized experiences.