Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
This seminar from the Center for Language & Speech Processing (CLSP) at Johns Hopkins University features Dr. Ting-Hao "Kenneth" Huang exploring the evolving relationship between humans and large language models (LLMs) in data annotation processes. Discover how traditional crowdsourcing methods compare to LLM performance in labeling quality, and examine the shifting role of humans from manual annotators to model instructors through prompting. Learn about the challenges of "prompting in the dark" - creating effective prompts without access to gold-standard labels - and its implications for annotation quality. Dr. Huang, an Associate Professor at Penn State's College of Information Sciences and Technology, brings expertise in natural language processing and human-computer interaction to this discussion, drawing from his award-winning research in developing interactive systems that support social and creative goals in everyday activities. His work spans scientific figure captioning, community advocacy tools, conversational systems, and creative writing assistance, with publications in top HCI, NLP, and AI conferences.
