Dispersion relations have been applied to hard exclusive processes suggesting that generalized parton distributions can be fully determined from their values on a kinematical ridge. We show significant pitfalls associated that vitiate this approach. We suggest an improved treatment of this assumption. Secondly, in order for a partonic interpretation to hold throughout the accessible kinematic region, semi-disconnected diagrams should not contribute. We show, however, that this condition is not satisfied for non-forward kinematics at leading order. Lastly we present our recent flexible parameterization of GPDs and indicate its application to neutral pseudoscalar electroproduction.