Logit Distance Bounds Representational Similarity
arXiv:2602.15438v1 Announce Type: new Abstract: For a broad family of discriminative models that includes autoregressive language models, identifiability results imply that if two models induce …
Beatrix M. B. Nielsen, Emanuele Marconato, Luigi Gresele, Andrea Dittadi, Simon Buchholz
5 views
