Using LLMs to evaluate the output of other AI models is an interesting proposition. After all, today's LLMs are increasingly capable and efficient, and the potential time and cost savings are enticing. But using an LLM to evaluate your model may not be the silver bullet you're looking for.
Join ML Evangelist Micaela Kaplan as she explores:
- Where the concept of LLM-as-a-Judge comes from and how it has developed over time
- The pros and cons of using LLM-as-a-Judge and where it does and doesn't work well
- How to mitigate the risks that come with using LLM-as-a-Judge
Speakers
Micaela Kaplan
Machine Learning Evangelist, [object Object]
Micaela Kaplan is the Machine Learning Evangelist at HumanSignal. With her background in applied Data Science and a masters in Computational Linguistics, she loves helping other understand AI tools and practices.