주제: Safe and Trustworthy LLMs

연사: 이화란 교수님

<약력>

- Ph.D., KAIST

- Assistant Professor, Sogang University

- (전) Lead Research Scientist, Naver AI Lab

- (전) Research Scientist, SK T-Brain

<연구 분야>

Building Trustworthy and Safe Large Language Models

<세부 분야>

• Construction of safety datasets, benchmarks, and evaluation metrics

• Controllable language generation

• LLM security, including adversarial attacks and red-teaming

• Safety alignment and learning methods