The inclusion of dispersion (van der Waals, vdW) forces in first-principles modeling of disordered chalcogenides is analyzed and critically discussed in view of their impact on the atomic structure. To this purpose we considered the case of glassy GeTe4. We selected a vdW correction (termed vdW(G) hereafter) introduced by Grimme (2006) and, as an alternative, the approach (termed vdW(W) hereafter) based on the Wannier functions formalism (Silvestrelli, 2008). It appears that a strategy based on the update of the vdW interactions due to changes in the electronic structure during the dynamical evolution (i.e., the vdW(W) one) provides results clearly different from those obtained in the vdWG framework. By keeping in mind that the nature of the present results is preliminary and reflect a trend to be confirmed, we draw attention to the different levels of agreement with experimental data obtained with the two vdW schemes employed.