There seems to be a reduction in psychological dependence in people treated with benzos and barbiturates for seizure disorders compared to people who don't have seizure disorders.

https://pmc.ncbi.nlm.nih.gov/articles/PMC6494026/

I think other disorders in gaba/glutamate functioning (or in an adjacent disorder that affects these systems) could be similar.

My guess is that low doses of benzos used to treat neurological disorders have a lower risk because GABA/Glutamate/related systems in that population are pathologically dysfunctional and benefit more directly from these medications.