[hanselot]

Giving examples of bias is as important imo, give it the unbiased facts as well as the biased ones so it can generalise relative objectivity.

[I_Am_Nous]

I agree with you, but I also wonder how the bias could be trained without it affecting the output of the entire model. Weights can help but anything that's higher weighted is just "less wrong" as I understand it, so I can see a possibility where training to expose bias might let bias creep in somewhat more than anticipated.