
Are Emergent Behaviors in LLMs an Illusion? with Sanmi Koyejo - #671
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Exploring Evaluation Challenges in Large Language Models
This chapter explores the intricate process of assessing large language models, focusing on the differences between standalone models and those enhanced with retrieval mechanisms. It also discusses the challenges of evaluation methodologies, data contamination, and the impact of surrounding systems on model performance.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.