causal

Amortized inference explains LLM Bayesian-like behavior

LLMs approximate Bayesian posteriors not by explicit factorized hypothesis updating but by amortizing inference through long learning, mapping novel contexts into Bayesian-like approximators in their activations after weights are frozen.

causalpending

Speaker

Chandra Sripada

Evidence Quote

“It turns out that you can approximate the Bayesian posterior... not by explicitly going through a factorized representation, but in a sense by modeling it or learning it”

Source

363 | Chandra Sripada on How LLMs and Humans are Cognitive Cousins— Sean Carroll's Mindscape
Created: 11/17/2026, 6:53:48 AM

Your notes

Loading notes...