talk-data.com talk-data.com

Event

Prompting for Production: Ensuring the Quality of LLM Outputs in Product Feature

2024-10-24 โ€“ 2024-10-24 Meetup Visit website โ†—

Activities tracked

2

We are thrilled to host and launch this event in cooperation with the Meetup.ai Berlin community.๐Ÿ’ฅ โœ… Registration: to attend the meetup, please RSVP on the Meetup.ai Berlin community page โžก๏ธ here โฌ…๏ธ.

๐Ÿ’ฅ Agenda: 17:30 Doors open: Time for mingling and networking with fellows; drinks will be served 18:00 Opening notes 18:10 Talk "Prompting for Production: Ensuring the Quality of LLM Outputs in Product Features at Grammarly" by Yulia Khalus, Computational Linguist at Grammarly 18:40 Break 18:45 Fireside Chat "Evaluating quality in LLM models pre-production" with Guy Rom, NLP consultant, ex-ML Researcher at Google Research 19:15 Community round pitch 19:30 Networking 21:00 Meetup ends

๐Ÿ’ฅ Prompting for Production: Ensuring the Quality of LLM Outputs in Product Features at Grammarly ๐Ÿ”ˆ Yulia Khalus - Computational Linguist at Grammarly ๐Ÿš€ 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.

โœ… Where: In-person, Grammarly Berlin hub โœ… When: Thursday, October 24 โœ… Language: English โœ… Registration: to attend the meetup, please RSVP on the Meetup.ai Berlin community. โžก๏ธ here โฌ…๏ธ

Sessions & talks

Showing 1โ€“2 of 2 ยท Newest first

Search within this event →

Fireside Chat "Evaluating quality in LLM models pre-production" with Guy Rom

2024-10-24
talk

Fireside chat on evaluating quality in LLM models pre-production.

Prompting for Production: Ensuring the Quality of LLM Outputs in Product Features at Grammarly

2024-10-24
talk
Yulia Khalus (Grammarly)

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.