There are some issues with multi–objective estimation of distribution algorithms (MOEDAs) that have been undermining their performance when dealing with problems with many objectives. In this paper we examine the model–building issue related to estimation of distribution algorithms (EDAs) and show that some of their, as yet overlooked, characteristics render most current MOEDAs unviable in the presence of many objectives. First, we present model–building as a problem with particular requirements and explain why some current approaches cannot properly deal with some of these conditions. Then, we discuss the strategies proposed for adapting EDAs to this problem. To validate our working hypothesis, we carry out an experimental study comparing different model–building algorithms. In the final part of the paper, we provide an in–depth discussion on viable alternatives to overcome the limitations of current MOEDAs in many–objective optimization.