Exploring Grounding and Compositionality
Dive into the fascinating world of grounding and compositionality in large language models (LLMs) with Daniel and Raphaël. Discover how LLMs form vector representations of words and explore the question of whether these representations hold inherent meaning. Gain insights into the connection between linguistic items and the objects they refer to in the world.In this clip
From this podcast
The Gradient
Raphaël Millière: The Vector Grounding Problem and Self-Consciousness
Related Questions