Large language models can behave deterministically at standard settings, so iterated-learning priors may be artifacts, and varying the starting point can reveal which models are truly sampling.
The claude 3 model family: Opus, sonnet, haiku, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do Language Models Have Bayesian Brains? Distinguishing Stochastic and Deterministic Decision Patterns within Large Language Models
Large language models can behave deterministically at standard settings, so iterated-learning priors may be artifacts, and varying the starting point can reveal which models are truly sampling.