Vitali Henne

Activities

1

talks

Software Engineer Grammarly

Filtering by: How We Use LLMs and Human Evaluations to Ensure High Quality of Suggestions ×

Filter by Event / Source

How We Use LLMs and Human Evaluations to Ensure High Quality of Suggestions 1

Talks & appearances

Showing 1 of 1 activities

Search activities →

In-house solution for conducting human-powered quality evaluations at scale

2024-09-26 · How We Use LLMs and Human Evaluations to Ensure High Quality of Suggestions

talk

Overview of Grammarly's in-house solution for conducting quality evaluations of suggestions, including what human quality evaluations are, how the solution provides insights into the impact and quality of new features before deployment, and a deep dive into the scalable, distributed design of the solution.