LLMs have unlocked new opportunities in NLP with their possible applications. Features that used to take months to be planned and developed now require a day to be prototyped. But how can we make sure that a successful prototype will turn into a high-quality feature useful for millions of customers? In this talk, we will explore real examples of the challenges that arise when ensuring the quality of LLM outputs and how we address them at Grammarly.
talk-data.com
Y
Speaker
Yulia Khalus
1
talks
Computational Linguist
Grammarly
Yulia Khalus—сomputational linguist at Grammarly. Works on such features as correctness, enhancement, and quick replies. Background: MA in translation (French-Ukrainian).
Bio from: The Depth and Breadth of Language Research and Engineering at Grammarly
Filtering by:
Prompting for Production: Ensuring the Quality of LLM Outputs in Product Feature
×
Filter by Event / Source
Talks & appearances
Showing 1 of 3 activities