Saved in:
Bibliographic Details
Main Authors: Toborek, Vanessa, Müller, Sebastian, Bauckhage, Christian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.01488
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.