LLMs are Bayesian, In Expectation, Not in Realization

Abstract

Bayesian accounts of in-context learning face a direct objection: exact posterior predictives for exchangeable data are invariant to task-preserving order, yet transformers change next-token probabilities when the same examples are serialized differently. We show this objection targets a structural invariant rather than the quantity scoring online prediction. For any Bayesian reference, excess prequential code length is exactly cumulative predictive KL. For unordered support sets that must be serialized, the expected regret of a single admissible ordering decomposes into that of the order-averaged predictor plus an order-averaging gain. Exchangeability violations are therefore not binary refutations; they are priced by log loss. We instantiate the theory with KT/Dirichlet finite-alphabet prediction and coarsened Bayesian linear-regression (BLR) predictive distributions. On Qwen2.5-7B/14B, floored candidate distributions at support $256$ have one-step excess code lengths of $0.020/0.011$ bits for Bernoulli and $0.039/0.022$ bits for four-way categorical prediction, with candidate mass above $0.999$; coarsened BLR continuations increasingly match the posterior-predictive digit distribution as support grows. A frequentist plug-in baseline sharpens the reading: the predictive distributions sit closer to the Bayesian posterior predictive than to the maximum-likelihood plug-in, by a margin largest at small support, where the plug-in is degenerate, and vanishing as the references converge. Position interventions and a from-scratch ablation localize order sensitivity to the positional encoding, activation patching tests causal use of decoded sufficient statistics, and permutation mixtures quantify the downstream log-loss cost of arbitrary orderings. Transformers need not realize exchangeable posterior predictives for every serialization to be Bayes-competitive prequential predictors.