# Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models

arXiv: https://arxiv.org/abs/2602.12937 · HTML: https://mlsanity.com/paper/2602.12937/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Builds on (most cited first, 15 of 15)

- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic](https://mlsanity.com/paper/2101.01785/) (2020)
- [Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier](https://mlsanity.com/paper/2412.04261/) (2024)
- [What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning](https://mlsanity.com/paper/1911.03090/) (2019)
- [NADI 2020: The First Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2010.11334/) (2020)
- [Arabic Dialect Identification in the Wild](https://mlsanity.com/paper/2005.06557/) (2020)
- [NADI 2021: The Second Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2103.08466/) (2021)
- [NADI 2023: The Fourth Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2310.16117/) (2023)
- [ALDi: Quantifying the Arabic Level of Dialectness of Text](https://mlsanity.com/paper/2310.13747/) (2023)
- [NADI 2022: The Third Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2210.09582/) (2022)
- [NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2407.04910/) (2024)
- [Arabic Dialect Identification under Scrutiny: Limitations of Single-label Classification](https://mlsanity.com/paper/2310.13661/) (2023)
- [Automatic Arabic Dialect Identification Systems for Written Texts: A Survey](https://mlsanity.com/paper/2009.12622/) (2020)
- [Common Ground, Diverse Roots: The Difficulty of Classifying Common Examples in Spanish Varieties](https://mlsanity.com/paper/2412.11750/) (2024)

## Abstract (arXiv)

Being modeled as a single-label classification task for a long time, recent work has argued that Arabic Dialect Identification (ADI) should be framed as a multi-label classification task. However, ADI remains constrained by the availability of single-label datasets, with no large-scale multi-label resources available for training. By analyzing models trained on single-label ADI data, we show that the main difficulty in repurposing such datasets for Multi-Label Arabic Dialect Identification (MLADI) lies in the selection of negative samples, as many sentences treated as negative could be acceptable in multiple dialects. To address these issues, we construct a multi-label dataset by generating automatic multi-label annotations using GPT-4o and binary dialect acceptability classifiers, with aggregation guided by the Arabic Level of Dialectness (ALDi). Afterward, we train a BERT-based multi-label classifier using curriculum learning strategies aligned with dialectal complexity and label cardinality. On the MLADI leaderboard, our best-performing LAHJATBERT model achieves a macro F1 of 0.69, compared to 0.55 for the strongest previously reported system. Code and data are available at https://mohamedalaa9.github.io/lahjatbert/.