Live Session
Chamber of Commerce
Poster
16 Oct
 
8:00
CEST
Wednesday Posters
Add Session to Calendar 2024-10-16 08:00 am 2024-10-16 05:30 pm Europe/Rome Wednesday Posters Wednesday Posters is taking place on the RecSys Hub. Https://recsyshub.org
Industry Poster

Leveraging LLM generated labels to reduce bad matches in job recommendations

View on ACM Digital Library

Yingchi Pei (Indeed.com), Yi Wei Pang (Indeed.com), Nilanjan Sengupta (Indeed.com) and Dheeraj Toshniwal (Indeed.com)

View Paper PDFView Poster
Abstract

Negative signals are increasingly employed to enhance recommendation quality. However, explicit negative feedback is often sparse and may disproportionately reflect the preferences of more vocal users. Commonly used implicit negative feedback, such as impressions without positive interactions, has the limitation of not accurately capturing users' true negative preferences because users mainly pursue information they consider interesting. In this work, we present an approach that leverages fine-tuned Large Language Models (LLMs) to evaluate matches and generate negative signals at scale while maintaining cost efficiency. We demonstrate significant improvements in recommendation quality by deploying a traditional classifier trained using LLM-generated labels.

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.