Elena Labzina, PhD

AI Research × ML Engineering

Current focus on AI safety, model behavior, and human–AI interaction.

Production ML, LLM and retrieval systems, experimentation, and large-scale evaluation at Google and Microsoft · Previous academic research at ETH Zürich

Research

Previous work on online propaganda, coordinated behavior, and adversarial manipulation of information on Wikipedia and Twitter. Current research examines LLM sycophancy, individual differences between users, and extended human–AI interaction.

Publications

Current study

Pre-screening volunteers for a study on how AI assistants affect people's beliefs.

Learn more and participate