You might be able to kludge a fix to tokenize the output and replace he/him/she/her with them/their. It's not as sexy as the engine outputting the correct words, but it should get the job done.
Yes, in this case as long as they still agree when it actually names people, I don't think it would be too difficult. There may be factors I'm not considering though.
Harder would be more general models like GPT-2 and GPT-3.
