factual

LLMs Fail Center Embedding Like Humans

Large language models fail to complete deeply center-embedded (nested) sentences in exactly the same way humans do, despite not being explicitly trained to fail, suggesting they may be modeling the way human language form is processed and generated.

factualpending

Speaker

Edward Gibson

Evidence Quote

“Neither can a large language model. They’re just like humans in that.”

Source

Edward Gibson— Lex Fridman Podcast
Created: 6/13/2026, 3:34:36 AM

Your notes

Loading notes...