As Large Language Models (LLMs) demonstrate impressive capabilities, demys-tifying their internal mechanisms becomes increasingly vital.

Arya et al. suggest using either supervised or self-supervised learning techniques to train the NN; the former requires access to exact inference

Multi-class / multi-taskarchitecture.Let l correspondtothetargetclassyl inthemulti-class setting.

However, NAMs (likeallGAMs), are not causal models.

They perform similarly to existing state-of-the-art generalized additive models in accuracy,but are more flexible because theyare based on neural nets instead ofboosted trees.

As Large Language Models (LLMs) demonstrate impressive capabilities, demys-tifying their internal mechanisms becomes increasingly vital.

Arya et al. suggest using either supervised or self-supervised learning techniques to train the NN; the former requires access to exact inference

Despite the current enthusiasm for GAMs, their susceptibility to concurvity - i.e., (possibly nonlinear) dependencies between the features - has hitherto been largely overlooked.