Guardado en:
Detalles Bibliográficos
Autores principales: Toborek, Vanessa, Müller, Sebastian, Bauckhage, Christian
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.01488
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Tabla de Contenidos:
  • Curriculum Learning (CL) aims to improve the outcome of model training by estimating the difficulty of samples and scheduling them accordingly. In NLP, difficulty is commonly approximated using task-agnostic linguistic heuristics or human intuition, implicitly assuming that these signals correlate with what neural models find difficult to learn. We propose a four-quadrant categorisation of difficulty signals -- human vs. model and task-agnostic vs. task-dependent -- and systematically analyse their interactions on a natural language understanding dataset. We find that task-agnostic features behave largely independently and that only task-dependent features align. These findings challenge common CL intuitions and highlight the need for lightweight, task-dependent difficulty estimators that better reflect model learning behaviour.