Lera Lakusta

Activities

1

talks

computational linguist Grammarly

Computational linguist at Grammarly. Focuses on improving quality of LLM outputs and applying linguistic approaches to prompt design and postprocessing.

Bio from: How We Build High-Quality, User-Oriented LLM Features at Grammarly

Filtering by: How We Build High-Quality, User-Oriented LLM Features at Grammarly ×

Filter by Event / Source

How We Build High-Quality, User-Oriented LLM Features at Grammarly 1

Talks & appearances

Showing 1 of 1 activities

Search activities →

Beyond generation: How to get high-quality text from LLMs

2025-08-26 · How We Build High-Quality, User-Oriented LLM Features at Grammarly

talk

llms prompt engineering text quality linguistic approaches

How can we influence quality during the prompt creation stage, as well as how to work with already-generated text—improving it, identifying errors, and filtering out undesirable results. We'll explore linguistic approaches that help achieve better, more controlled outcomes from LLMs.