# Four Quadrants of Difficulty: A Simple Categorisation and its Limits

arXiv: https://arxiv.org/abs/2601.01488 · HTML: https://mlsanity.com/paper/2601.01488/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 4 Jan 2026.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation](https://mlsanity.com/paper/2211.02570/) (2022)
- [A Corpus for Automatic Readability Assessment and Text Simplification of German](https://mlsanity.com/paper/1909.09067/) (2019)
- [Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification](https://mlsanity.com/paper/2310.08170/) (2023)
- [Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLU](https://mlsanity.com/paper/2210.12499/) (2022)
- [LCP-RIT at SemEval-2021 Task 1: Exploring Linguistic Features for Lexical Complexity Prediction](https://mlsanity.com/paper/2105.08780/) (2021)
- [Beyond Shallow Heuristics: Leveraging Human Intuition for Curriculum Learning](https://mlsanity.com/paper/2508.19873/) (2025)
- [HuCurl: Human-induced Curriculum Discovery](https://mlsanity.com/paper/2307.07412/) (2023)

## Abstract (arXiv)

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.