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

Exploring LLM Limitations and Potential

This chapter critically examines the limitations of large language models (LLMs) in understanding and applying complex reasoning, particularly in diverse contexts. It discusses misconceptions about LLM capabilities, contrasting them with human cognitive processes, and emphasizes the need for exploring alternative AI architectures for improved reasoning. The conversation also introduces innovative frameworks like LLM Modulo to enhance integration and effectiveness in reasoning tasks.

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