Live Session
Teatro Petruzzelli
Paper
15 Oct
 
10:15
CEST
Session 1: Large Language Models 1
Add Session to Calendar 2024-10-15 10:15 am 2024-10-15 11:00 am Europe/Rome Session 1: Large Language Models 1 Session 1: Large Language Models 1 is taking place on the RecSys Hub. Https://recsyshub.org
Industry

Playlist Search Reinvented: LLMs Behind the Curtain

View on ACM Digital Library

Geetha Aluri (Amazon), Siddharth Sharma (Amazon), Tarun Sharma (Amazon) and Joaquin Delgado (Amazon)

View Paper PDFView Poster
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.

Join the Conversation

Head to Slido and select the paper's assigned session to join the live discussion.

Conference Agenda

View Full Agenda →
No items found.