This is very topical given the amount of hype and noise around LLMs.
I am excited to open up my course on Large Language Models (LLMs) at the University of Pennsylvania to a broader audience through a virtual lecture series, sponsored by Turing. Join us on Monday, September 23rd, from 1:45 PM - 3:15 PM ET for the first in this series, featuring Yann Dubois, Ph.D. candidate at Stanford University advised by Percy Liang and Tatsu Hashimoto. Yann will talk about "Scalable Evaluation of Large Language Models". Register here: https://lu.ma/or7gm94o Abstract: Evaluation is a cornerstone of machine learning, critical for model development and selection. For LLMs like ChatGPT, evaluation presents unique challenges due to the open-ended nature of their outputs. While human evaluation remains the gold standard, its cost and time-intensive nature make it impractical for rapid development cycles. This talk will provide an overview of scalable approaches to LLM evaluation, focusing on using one LLM to evaluate another. I will discuss the potential benefits and limitations of this approach and explore mitigation strategies for its challenges. This is just the beginning! Stay tuned for more lectures coming online from this course. #ai #machinelearning #largelanguagemodels #llm #upenn #turing