Machine Learning Street Talk (MLST) cover image

Prof. Subbarao Kambhampati - LLMs don't reason, they memorize (ICML2024 2/13)

Machine Learning Street Talk (MLST)

00:00

Challenges of Fine-Tuning Large Language Models in Problem Domains

This chapter explores the intricacies of applying large language models in specific domains, focusing on accuracy issues and the expenses of fine-tuning. It critiques the effectiveness of LLMs for tasks like arithmetic, raising questions about the rationale for costly enhancements that offer minimal improvements over traditional approaches.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app