Topic
Model Evaluation
Discover key takeaways from 2 podcast episodes about this topic.
Large Language ModelsAI SafetyMachine Unlearning
Jun 10, 2026Atomic Facts to Structured Knowledge: Rethinking Unlearning & Jailbreaking in Large Language Models
This talk reveals how the interconnected nature of knowledge within Large Language Models creates fundamental vulnerabilities, enabling sophisticated jailbreaking attacks and undermining current unlearning methods.
Large Language Models (LLMs)Data MemorizationCopyright Infringement
Jan 27, 2026Evaluating Data Misuse in LLMs: Introducing Adversarial Compression Rate as a Metric of Memorization
This presentation introduces Adversarial Compression Rate (ACR) as a robust metric to quantify LLM memorization, addressing copyright concerns by focusing on the shortest prompt needed to elicit exact verbatim output.
G
Google TechTalks