# Aladdin-FTI @ AMIYA Three Wishes for Arabic NLP: Fidelity, Diglossia, and Multidialectal Generation

arXiv: https://arxiv.org/abs/2602.16290 · HTML: https://mlsanity.com/paper/2602.16290/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 45 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.16039/) (2023)
- [Understanding and Mitigating Language Confusion in LLMs](https://mlsanity.com/paper/2406.20052/) (2024)
- [Unsupervised Statistical Machine Translation](https://mlsanity.com/paper/1809.01272/) (2018)
- [A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods](https://mlsanity.com/paper/2204.03508/) (2022)
- [Curras + Baladi: Towards a Levantine Corpus](https://mlsanity.com/paper/2205.09692/) (2022)
- [AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal Arabic](https://mlsanity.com/paper/2412.04193/) (2024)
- [The Evolution of Darija Open Dataset: Introducing Version 2](https://mlsanity.com/paper/2405.13016/) (2024)
- [Saudi-Dialect-ALLaM: LoRA Fine-Tuning for Dialectal Arabic Generation](https://mlsanity.com/paper/2508.13525/) (2025)
- [Arabizi vs LLMs: Can the Genie Understand the Language of Aladdin?](https://mlsanity.com/paper/2502.20973/) (2025)

## Built on by (most cited first, 1 of 1)

- [IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variation](https://mlsanity.com/paper/2604.04704/) (2026)

## Abstract (arXiv)

Arabic dialects have long been under-represented in Natural Language Processing (NLP) research due to their non-standardization and high variability, which pose challenges for computational modeling. Recent advances in the field, such as Large Language Models (LLMs), offer promising avenues to address this gap by enabling Arabic to be modeled as a pluricentric language rather than a monolithic system. This paper presents Aladdin-FTI, our submission to the AMIYA shared task. The proposed system is designed to both generate and translate dialectal Arabic (DA). Specifically, the model supports text generation in Moroccan, Egyptian, Palestinian, Syrian, and Saudi dialects, as well as bidirectional translation between these dialects, Modern Standard Arabic (MSA), and English. The code and trained model are publicly available.