Live Session
Session 1: Large Language Models 1
Industry
Playlist Search Reinvented: LLMs Behind the Curtain
Geetha Aluri (Amazon), Siddharth Sharma (Amazon), Tarun Sharma (Amazon) and Joaquin Delgado (Amazon)
Abstract
Improving search functionality poses challenges such as data scarcity for model training, metadata enrichment for comprehensive document indexing, and the labor-intensive manual annotation for evaluation. Traditionally, iterative methods relying on human annotators and customer feedback have been used. However, recent advancements in Large Language Models (LLMs) offer new solutions. This paper focuses on applying LLMs to playlist search in Amazon Music. Leveraging LLMs’ contextual understanding and generative capabilities automates metadata enrichment, reducing manual efforts and expediting training. LLMs also address data scarcity by generating synthetic training data and serve as scalable judges for evaluation, enhancing search performance assessment. We demonstrate how these innovations enhance playlist search, overcoming traditional limitations to improve search result accuracy and relevance.