causal
Embers of Autoregression Bias
Raw language models like GPT-4 are very sensitive to the probability of the outputs they must produce: they are better at counting strings of 30 letters than 29 because the number 30 appears more often on the internet than 29, so when nearby high-probability answers exist the model produces the high-probability one rather than the correct one—an idiosyncratic bias the authors called 'embers of autoregression.'
causalpending
Speaker
Tom GriffithsEvidence Quote
“it sort of produces the high probability thing rather than the thing that it's supposed to produce. And so that's a sort of like weird idiosyncratic bias of language models.”
Created: 6/13/2026, 12:12:58 AM
Your notes
Loading notes...