Extensions and improvements of empirical force fields are discussed in view of applications to computational vibrational spectroscopy and reactive molecular dynamics simulations. Particular focus is on quantitative studies, which make contact with experiments and provide complementary information for a molecular-level understanding of processes in the gas phase and in solution. Methods range from including multipolar charge distributions to reproducing kernel Hilbert space approaches and machine learned energy functions based on neural networks. © 2020 Author(s).