Dose XRTransformer support relevance score of label

[xchen-chwy]

In this tutorial example https://github.com/amzn/pecos/blob/mainline/tutorials/kdd22/Session%202%20Extreme%20Multi-label%20Classification%20with%20PECOS.ipynb. it gives an example of

The data file format also supports to represent the label relevance for cost-sensitive learning by using double colons to separate a label and its relevance.

0::0.1,1::0.2,2::0.8 <TAB> Alan Turing is widely considered to be the father of theoretical computer science and artificial intelligence.

but when read thought the code, it seems in PECOS, only the XLinear model explicitly supports relevance scores for labels, while XRTransformer primarily focuses on multi-label classification without directly supporting relevance scores, is it True? if I would like to use XRTransformer with relevance score for labels, any suggestions? Looking forward to hearing back, Thank you!