Challenges in Making LLMs Safe and Robust
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=0_Ui4y_v0Mw
0Aditi Raghunathan (Carnegie Mellon University)
https://simons.berkeley.edu/talks/aditi-raghunathan-carnegie-mellon-university-2024-09-06
Special Year on Large Language Models and Transformers, Part 1 Boot Camp
Aditi Raghunathan (CMU)’s presentation in the Large Language Models and Transformers, Part I Boot Camp addresses the root causes of numerous safety concerns and wide-ranging attacks on current large language models. Using a simple illustrative problem, she walks us through several defense strategies and evaluates their strengths and weaknesses, drawing connections to the broader literature on safety and robustness in machine learning.