Expansion of a disease-specific tandem repeat is responsible for >45 Repeat Expansion Diseases (REDs). The expansion mutation in each of these diseases has different pathological consequences and most are currently incurable. If the underlying mechanism of mutation is shared, a strategy that slows repeat expansion in one RED may be applicable to multiple REDs. However, the fact that PMS2, a component of the MutL mismatch repair complex, promotes expansion in some models and protects against it in others, suggests that the expansion mechanisms may differ. We show here using mouse models of two REDs caused by different repeats that the seemingly paradoxical effects of PMS2 do not reflect different expansion mechanisms but rather cell-type and dosage effects in different tissues. This differential effect is recapitulated in mouse embryonic stem cells with inducible PMS2 expression: PMS2 promotes expansion at low concentrations, an effect that requires a functional nuclease domain; while at higher concentrations it protects against expansion. The apparent paradoxical behavior of PMS2 can be resolved in a model based on the different in vitro cleavage preferences of MutL and MutL{gamma}, another MutL complex known to be required for expansion. Our data thus resolve a longstanding puzzle and suggest a common mechanism responsible for REDs. Our data also provide proof of concept that increasing PMS2 levels suppresses repeat expansion not only in cells where its loss promotes expansion, but also in cells that require it for expansion, supporting its potential as a broadly applicable therapeutic strategy.