Compartmentalization: Learning to Translate Is Not Learning to Transfer

Language models learn from data presented in many surface forms; they train on the same facts in English and Swahili, the same functions in Python and Haskell. Ideally, what a model learns from one form should help it with others. We test a variant of this in a controlled setting by rendering the same text in $c$ _compartments_ that use disjoint vocabularies, each a token-for-token relabeling of the others. Models up to 42M parameters trained on 131B tokens often learn each compartment about as slowly as if trained on its share of the data alone, a failure we call _compartmentalization_. Models initialized with identical embeddings across compartments show no such cost, so a unified solution exists, but is not found from generic initialization. Paired examples, each showing the same text in two compartments, teach models to convert between compartments almost perfectly (99.7-100% exact match), but this reduces the sample efficiency cost only past a threshold determined by $c$ and the learning rate. Learning a mapping between surface forms, in other words, does not guarantee transfer between them.