Watch On Demand

The MLOps Live Webinar Series

Session #27

Watch On Demand

On Demand

LLM Validation & Evaluation

Data labelling at scale has become a massive challenge in AI, with the rapidly growing use of LLMs for diverse use cases such as call center analysis, chatbots, personal assistants and more.

How can you validate, evaluate and fine tune an LLM effectively? Is there a way to automatically label data to improve model efficiency, without needing to employ hundreds or thousands of human data labelers?

In this webinar we discussed:

  • How to effectively validate and evaluate your LLM
  • A real world use case
  • A deep dive into the pipeline showing how automation can be used across the board—from data labeling at scale, to deploying and managing your gen AI application in production.

Watch this session to learn firsthand how to build an automated flow to accelerate and streamline your gen AI applications start to finish!

Presented By
Ehud Barnea

PHD, Head of AI, Tasq.ai

Yaron Haviv

Co-Founder and CTO, Iguazio 

Guy Lecker

ML Engineering Team Lead, Iguazio