Saved in:
| Main Authors: | , , |
|---|---|
| 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!
|
| _version_ | 1866911353237667840 |
|---|---|
| author | Toborek, Vanessa Müller, Sebastian Bauckhage, Christian |
| author_facet | Toborek, Vanessa Müller, Sebastian Bauckhage, Christian |
| 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01488 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Four Quadrants of Difficulty: A Simple Categorisation and its Limits Toborek, Vanessa Müller, Sebastian Bauckhage, Christian Computation and Language Machine Learning 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. |
| title | Four Quadrants of Difficulty: A Simple Categorisation and its Limits |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2601.01488 |