Enregistré dans:
Détails bibliographiques
Auteurs principaux: Naim, Omar, Bolte, Jerome, Asher, Nicholas
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2502.03503
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
Table des matières:
  • Our paper challenges claims from prior research that transformer-based models, when learning in context, implicitly implement standard learning algorithms. We present empirical evidence inconsistent with this view and provide a mathematical analysis demonstrating that transformers cannot achieve general predictive accuracy due to inherent architectural limitations.