Yulia Khalus

Activities

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

Filter by Event / Source

The Depth and Breadth of Language Research and Engineering at Grammarly 1 How We Build High-Quality, User-Oriented LLM Features at Grammarly 1 Prompting for Production: Ensuring the Quality of LLM Outputs in Product Feature 1

Talks & appearances

Showing 1 of 3 activities

Search activities →

Users or experts? Navigating the trade-offs in LLM quality annotation

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

talk

llms linguistic annotation NLP user studies

In this talk, we will examine how LLM outputs are evaluated by potential end users versus professional linguist-annotators, as two ways of ensuring alignment with real-world user needs and expectations. We will compare the two approaches, highlight the advantages and recurring pitfalls of user-driven annotation, and share the mitigation techniques we have developed from our own experience.