How to use custom AI evaluators and LLM-as-a-judge to enhance data quality

Register now

Featured Speakers:

Trusted by leading Fortune 500 enterprises and AI-fueled companies

Trusted by leading startups and Fortune 500 enterprises

IBRAHIM MUHAMMAD

Software Engineering

Improve your data quality by learning how to use Labelbox's new AI-powered critics. You’ll discover the technical details of our built-in code and grammar critics, as well as how our brand new customizable AI critic enables you to use powerful LLMs and custom code. Join two senior Labelbox engineers to explore how these virtual assistants can be customized to automate the review of labels and responses to match your specific needs. By the end, you’ll know how to perform your own custom evaluations to improve the efficiency of your teams and to create intelligent labeling pipelines.

What you'll learn:

Understand why traditional quality assurance methods fall short and how AI-powered critics elevate data accuracy
Learn how to implement grammar, code, and custom evaluators tailored to your specific project needs
Discover how to leverage LLMs as judges within your custom evaluators to provide intelligent feedback and guidance to labelers

KAMIL KOZIK

Software Engineering

Host & Moderator

MICHAEL HAAG

Product Marketing

How to use custom AI evaluators and LLM-as-a-judge to enhance data quality

December 12, 2024 at 9am PT/12pm ET