I generally don't see racism "justified" in models but rather explained. And the explanation is always bad training data / gaps in training data. I am suggesting you train/modify it to cover training data deficiencies so you treat all hateful content with equal discretion.

But keep in mind even the approach you recommend carries its own US-centric bias. There are lots of countries that would want open racism against some groups but not others and dismiss your desires for egalitarian treatment as American arrogance.