[R] Connections between Uncertainty Quantification and AI Alignment?

Hi folks,

​

as the title suggests, I am looking for pointers (research papers or brainstorming ideas) that connect these two areas of ML.

for those not familiar with alignment, here's the most distinctive paper:

[https://arxiv.org/pdf/2203.02155.pdf](https://arxiv.org/pdf/2203.02155.pdf)

​

thanks!

​

​

ai alignment alignment ideas machinelearning paper papers quantification research research papers uncertainty