Good question. I originally defined train-deploy mismatch the way you suggest. On that definition, inoculation prompting is interpreted as changing the model architecture (by grafting the inoculation prompt onto it) during training. However, Monte convinced me that inoculation prompting is better understood as changing the data distribution, so I edited the post to be less committal and include that as a possibility too, even though I still think primarily in terms of the original definition.
Good question. I originally defined train-deploy mismatch the way you suggest. On that definition, inoculation prompting is interpreted as changing the model architecture (by grafting the inoculation prompt onto it) during training. However, Monte convinced me that inoculation prompting is better understood as changing the data distribution, so I edited the post to be less committal and include that as a possibility too, even though I still think primarily in terms of the original definition.