YandexHall and YerevaNN are excited to present ML OpenTalk December 2024 – Erik Arakelyan’s talk on “How to Reason Robustly, Verifiably, and Faithfully with LLMs.”
December 19, 7:00 PM
YandexHall, Moskovyan 35, Yerevan
Register here to secure your spot, link in the event.
Stay updated with YandexHall events:
Telegram: https://t.me/yandex_hall
Speaker: Erik Arakelyan, [LinkedIn](https://www.linkedin.com/in/erik-arakelyan-a6a84470/), [Google Scholar](https://scholar.google.it/citations?hl=en&user=63BfrxMAAAAJ)
About Erik
Erik Arakelyan is a Machine Learning researcher doing a Ph.D. at the University of Copenhagen (UCPH), specializing in topics of Neuro-symbolic AI, query answering over Knowledge Graphs, Large Language Models, and Explainability in NLP. Erik was a visiting researcher at Amazon working on grounded LLM reasoning and knowledge-based completion at Alexa AI and Amazon AGI. Creating scalable pipelines for experimentation and inference over KGs and researching multi-hop reasoning with retrieval-based augmentation over LLMs.
About the talk
During the talk, Erik will explain ways to improve large language models (LLMs)’ reasoning, or “thinking,” through problems to give accurate answers.
We’ll focus on key areas:
Starting with what we mean by “reasoning” for LLMs, we’ll look at how to train and guide models to make smart, context-aware responses.
Agenda
6:30 PM Registration
7:00 PM Talk and Q&A
8:15 PM – 8:45 PM Networking
You can find more tech events happening in Armenia here