---
title: "United Arab Emirates — research institutions, scientists and"
description: "United Arab Emirates: 7 institutions with papers in our library in 3 agglomerations, 56 people with a page, 81 works, 5,942 citations."
canonical: "https://research.elamur.ai/free/en/countries/united-arab-emirates/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/countries/united-arab-emirates/)

[home](https://md.research.elamur.ai/free/en/) / [countries](https://md.research.elamur.ai/free/en/countries/) / United Arab Emirates

# United Arab Emirates

Country 7 institutions in 3 agglomerations · [all countries](https://md.research.elamur.ai/free/en/countries/)

[**7** institutions with a page](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/#institutions) · [**3** agglomerations](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/#agglomerations) · [**56** people with a page](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/#authors) · [**81** works in our library](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/#works) · [**5,942** citations of their works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/#works)

## About

### Profile

The United Arab Emirates is represented on this site by a small group of universities and research institutes. Taken together, their work is mostly about language: how computers process Arabic, and how large language models are built, tested and kept honest. Five of the institutions are universities and two are research institutes. They sit in three urban areas.

The first is [Abu Dhabi](https://md.research.elamur.ai/free/en/agglomerations/abu-dhabi/). It holds most of the country's institutions on this site and nearly all of their cited work. The second is the [Dubai](https://md.research.elamur.ai/free/en/agglomerations/dubai/) area, represented by the University of Sharjah. The third is [Al Ain](https://md.research.elamur.ai/free/en/agglomerations/al-ain/), home to United Arab Emirates University.

Two Abu Dhabi universities carry most of the national output among the works here. [Mohamed bin Zayed University of Artificial Intelligence](https://md.research.elamur.ai/free/en/universities/mohamed-bin-zayed-university-of-artificial-intelligence/) has the most cited body of work. [New York University Abu Dhabi](https://md.research.elamur.ai/free/en/universities/new-york-university-abu-dhabi/) has the larger number of papers. Next come two research institutes in the capital, the [Technology Innovation Institute](https://md.research.elamur.ai/free/en/labs/technology-innovation-institute/) and the [Inception Institute of Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/inception-institute-of-artificial-intelligence/). Three further universities have smaller sets of work: the [University of Sharjah](https://md.research.elamur.ai/free/en/universities/university-of-sharjah/), [United Arab Emirates University](https://md.research.elamur.ai/free/en/universities/united-arab-emirates-university/) and [Zayed University](https://md.research.elamur.ai/free/en/universities/zayed-university/).

These institutions form part of the wider directory of [institutions](https://md.research.elamur.ai/free/en/orgs/) and of [countries](https://md.research.elamur.ai/free/en/countries/) on this site.

### History

The country's history on this site begins with Arabic language technology at New York University Abu Dhabi. The earliest work here dates from 2015: a study by Anas Shahrour, Salam Khalifa and Nizar Habash on [improving Arabic diacritization through syntactic analysis](https://md.research.elamur.ai/free/en/papers/shahrour-2015-improving-arabic-diacritization-through-syntactic/). It used parsing to choose better analyses than a narrow word window allows. A parser and disambiguation system called CamelParser followed in 2016.

In 2017 and 2018 this line widened in three directions:

neural morphological disambiguation; - an Arabic treebank in the Universal Dependencies framework; - a large morphological analyzer and generator, and unified spelling conventions for Arabic dialects.

The same years brought the multilingual parsing shared task of CoNLL 2017, which became one of the most cited works of the country on this site. At Al Ain, United Arab Emirates University appears in 2017 and 2019 with theoretical syntax: control structures in Amharic, then the verbal morphology of Emirati Arabic.

From 2020 the Arabic line produced the open-source CAMeL Tools toolkit and joint models for several morphological tasks. Work on Arabic grammatical errors began in 2021, the same year that sentiment classification for Arabic appears from Sharjah.

The second major line opens in 2022 and grows quickly through 2023 and 2024. It covers large language models: multilingual instruction tuning, prompt optimisation, open model families, Arabic-centric models, factuality, misinformation and the detection of machine-generated text. This work comes mainly from Mohamed bin Zayed University of Artificial Intelligence, the Technology Innovation Institute and the Inception Institute of Artificial Intelligence.

By 2025 and 2026 the works here turn toward evaluation and specialised resources:

a very hard general benchmark; - quality checks on Arabic benchmarks; - dialectal Arabic speech; - multi-label dialect identification; - multilingual detoxification; - language-guided robot navigation.

### Research profile

Across the country's works in our library, the dominant topic by far is [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/), and above all Arabic. In terms of fields, most works belong to [linguistics and languages](https://md.research.elamur.ai/free/en/shelves/linguistics/). A substantial group sits in [natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/). Smaller sets fall under [machine translation](https://md.research.elamur.ai/free/en/shelves/machine-translation/), [AI and machine learning](https://md.research.elamur.ai/free/en/shelves/ai/), and [mathematics and statistics](https://md.research.elamur.ai/free/en/shelves/mathematics/).

[Morphology](https://md.research.elamur.ai/free/en/topics/morphology/) is the second largest topic, and much of it is Arabic. Among the works here:

Zalmout and Habash argued in 2017 that classic morphological analyzers still help neural taggers. - The 2018 work on [noise-robust morphological disambiguation for dialectal Arabic](https://md.research.elamur.ai/free/en/papers/zalmout-2018-noise-robust-morphological-disambiguation-dialectal/) carried this approach to dialects. - The 2020 work on [joint diacritization, lemmatization, normalization and tagging](https://md.research.elamur.ai/free/en/papers/zalmout-2020-joint-diacritization-lemmatization-normalization-fine/) combined several tasks in one model. - Taji and colleagues built the CALIMA Star analyzer and generator. - Salam Khalifa took part in the multilingual inflection database [UniMorph 4.0](https://md.research.elamur.ai/free/en/papers/batsuren-2022-unimorph-4/).

Closely related are [tokenization and segmentation](https://md.research.elamur.ai/free/en/topics/tokenization/), [part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/), [dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/), [treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/) and [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/). Two works show these topics most clearly. One is [Universal Dependencies for Arabic](https://md.research.elamur.ai/free/en/papers/taji-2017-universal-dependencies-arabic/). The other is [CamelParser](https://md.research.elamur.ai/free/en/papers/shahrour-2016-camelparser-system-arabic-syntactic-analysis/), which joined syntactic analysis with morphological disambiguation.

[Language models and pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) form the third large cluster. It is the most cited one. It includes:

the Falcon model family from the Technology Innovation Institute; - Jais, an Arabic-centric model; - crosslingual multitask finetuning; - prompt optimisation by reinforcement learning; - a controlled study, Physics of Language Models, of how such models store and retrieve facts.

Next to these models stands work on [evaluation and benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/). Examples are ArabicMMLU, Humanity's Last Exam, TrustLLM and the QIMMA study of Arabic benchmark reliability. A related concern, [bias, fairness and safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/), runs through the works on factuality, misinformation pollution and detection of machine-generated text.

Several smaller topics complete the picture. In [machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), the works include document-level translation with large models and [TARJAMAT](https://md.research.elamur.ai/free/en/papers/kadaoui-2023-tarjamat-evaluation-bard-chatgpt-machine/), a test of chat systems on several Arabic varieties. The University of Sharjah contributes an Egyptian Arabic–English parallel corpus. Work on [multilingual and cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) and [low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) addresses languages with little data.

In [grammatical error correction](https://md.research.elamur.ai/free/en/topics/grammatical-error-correction/), New York University Abu Dhabi contributes [automatic error type annotation for Arabic](https://md.research.elamur.ai/free/en/papers/belkebir-2021-automatic-error-type-annotation-arabic/) and an [empirical study of Arabic error detection and correction](https://md.research.elamur.ai/free/en/papers/alhafni-2023-advancements-arabic-grammatical-error-detection/). Work on [sentiment and emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) comes from Sharjah and the Inception Institute. For [speech](https://md.research.elamur.ai/free/en/topics/speech/), the Bulbul dataset collects dialectal Arabic speech. There are also single works touching [question answering](https://md.research.elamur.ai/free/en/topics/question-answering/), [coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) and [implicature](https://md.research.elamur.ai/free/en/topics/implicature/).

### Leading scientists

[Preslav Nakov](https://md.research.elamur.ai/free/en/authors/preslav-nakov/), of Mohamed bin Zayed University of Artificial Intelligence, comes first among the people of the country on this site. The university's works here centre on large language models, their factuality and the spread of misinformation. Nakov's place belongs within that group.

[Nizar Habash](https://md.research.elamur.ai/free/en/authors/nizar-habash/), at New York University Abu Dhabi, has by far the most papers among the country's people here. Habash is the common thread of the Arabic line. Examples include:

diacritization through syntax; - neural disambiguation with Nasser Zalmout; - the Arabic Universal Dependencies treebank with Dima Taji; - the dialect orthography guidelines; - error-type annotation with Riadh Belkebir.

[Timothy Baldwin](https://md.research.elamur.ai/free/en/authors/timothy-baldwin/), of Mohamed bin Zayed University of Artificial Intelligence, co-wrote [Factuality Challenges in the Era of Large Language Models](https://md.research.elamur.ai/free/en/papers/augenstein-2023-factuality-challenges-era-large-language/) with Isabelle Augenstein and others. It is a position paper on the risks that fluent but inaccurate model output poses.

[Yuanzhi Li](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/) co-wrote with Zeyuan Allen-Zhu [Physics of Language Models: Part 3.1](https://md.research.elamur.ai/free/en/papers/allen-zhu-2023-physics-language-models-part-3/). The paper asks whether a model truly learns to extract facts from its training text or merely memorises surface patterns.

[Eric Xing](https://md.research.elamur.ai/free/en/authors/eric-xing/), [Alham Fikri Aji](https://md.research.elamur.ai/free/en/authors/alham-fikri-aji/), Kentaro Inui and [Xiaodan Liang](https://md.research.elamur.ai/free/en/authors/xiaodan-liang/) are also at Mohamed bin Zayed University of Artificial Intelligence. Their presence here falls within the same body of language-model research. So does that of AbdelRahim Elmadany and Thamar Solorio.

[Salam Khalifa](https://md.research.elamur.ai/free/en/authors/salam-khalifa/) of New York University Abu Dhabi appears on many of the Arabic resource papers: diacritization, CamelParser, the CALIMA Star analyzer, CAMeL Tools, the dialect orthography work and UniMorph 4.0.

[Fajri Koto](https://md.research.elamur.ai/free/en/authors/fajri-koto/) led ArabicMMLU together with [Haonan Li](https://md.research.elamur.ai/free/en/authors/haonan-li/). The benchmark collects native Arabic exam questions instead of relying on translated material.

Other researchers stand out within particular institutions:

At New York University Abu Dhabi: [Dima Taji](https://md.research.elamur.ai/free/en/authors/dima-taji/), [Ossama Obeid](https://md.research.elamur.ai/free/en/authors/ossama-obeid/), [Nasser Zalmout](https://md.research.elamur.ai/free/en/authors/nasser-zalmout/), [Bashar Alhafni](https://md.research.elamur.ai/free/en/authors/bashar-alhafni/) and [Alexander Erdmann](https://md.research.elamur.ai/free/en/authors/alexander-erdmann/). - At the Inception Institute of Artificial Intelligence: [Neha Sengupta](https://md.research.elamur.ai/free/en/authors/neha-sengupta/) and [Sunil Kumar Sahu](https://md.research.elamur.ai/free/en/authors/sunil-kumar-sahu/), who led the Jais paper. - At the Technology Innovation Institute: [Hamza Alobeidli](https://md.research.elamur.ai/free/en/authors/hamza-alobeidli/), among the authors of the Falcon paper. - At the University of Sharjah: [Ali Bou Nassif](https://md.research.elamur.ai/free/en/authors/ali-bou-nassif/) and [Ashraf Elnagar](https://md.research.elamur.ai/free/en/authors/ashraf-elnagar/), who worked on Arabic fake news and sentiment. - At United Arab Emirates University: [Tommi Leung](https://md.research.elamur.ai/free/en/authors/tommi-leung/), with work on syntactic theory.

### Landmark works

The most cited work of the country here is [Crosslingual Generalization through Multitask Finetuning](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-crosslingual-generalization-through-multitask-finetuning/) (2022). It asks whether instruction-style multitask finetuning still works when tasks and prompts span many languages.

Next is the [CoNLL 2017 shared task on multilingual parsing from raw text](https://md.research.elamur.ai/free/en/papers/zeman-2017-conll-2017-shared-task-multilingual/), with Daniel Zeman as first author. It required systems to parse unprocessed text into Universal Dependencies trees without gold tokenization, sentence splits or tags.

[The Falcon Series of Open Language Models](https://md.research.elamur.ai/free/en/papers/almazrouei-2023-falcon-series-open-language-models/) (2023) records how the Technology Innovation Institute pretrained its family of open causal decoder models. It is that institute's most cited contribution here.

[RLPrompt](https://md.research.elamur.ai/free/en/papers/deng-2022-rlprompt-optimizing-discrete-text-prompts/) (2022) searches with reinforcement learning for discrete text prompts that steer a frozen pretrained model.

[Document-Level Machine Translation with Large Language Models](https://md.research.elamur.ai/free/en/papers/wang-2023-document-level-machine-translation-large/) (2023) tests such models on whole-document translation. Its authors released prompts, outputs and annotations so the work can be repeated.

[CAMeL Tools](https://md.research.elamur.ai/free/en/papers/obeid-2020-camel-tools-open-source-python/) (2020) is the most cited of the Arabic-specific works. It is an open Python toolkit built around problems specific to Arabic: missing diacritics, rich inflection and dialect variation.

Two works from 2024 and 2025 deal with evaluation:

[Humanity's Last Exam](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/) answers the saturation of benchmarks such as MMLU with a much harder test. - [TrustLLM](https://md.research.elamur.ai/free/en/papers/huang-2024-trustllm-trustworthiness-large-language-models/) proposes a unified framework for judging whether models behave reliably.

Three works from 2023 sit nearby:

[Jais and Jais-chat](https://md.research.elamur.ai/free/en/papers/sengupta-2023-jais-jais-chat-arabic-centric/) introduced Arabic-centric foundation and chat models, trained on what its authors present as the largest Arabic pretraining set so far. - [On the Risk of Misinformation Pollution with Large Language Models](https://md.research.elamur.ai/free/en/papers/pan-2023-risk-misinformation-pollution-large-language/) studies false content entering information systems, whether through accidental hallucination or deliberate misuse. - [DetectLLM](https://md.research.elamur.ai/free/en/papers/su-2023-detectllm-leveraging-log-rank-information/) proposes zero-shot detection of machine-generated text from token log-rank scores.

In the Arabic line, [Unified Guidelines and Resources for Arabic Dialect Orthography](https://md.research.elamur.ai/free/en/papers/habash-2018-unified-guidelines-resources-arabic-dialect/) set out CODA*, a dialect-independent spelling convention. [ArabicMMLU](https://md.research.elamur.ai/free/en/papers/koto-2024-arabicmmlu-assessing-massive-multitask-language/) made a native Arabic benchmark. [Don't Throw Those Morphological Analyzers Away Just Yet](https://md.research.elamur.ai/free/en/papers/zalmout-2017-don-t-throw-those-morphological/) showed that analyzers and neural taggers work best in combination. From Sharjah, [Arabic Fake News Detection Based on Deep Contextualized Embedding Models](https://md.research.elamur.ai/free/en/papers/nassif-2022-arabic-fake-news-detection-based/) applied transformer embeddings to a task that has had far less attention in Arabic than in English.

### Labs and units

Mohamed bin Zayed University of Artificial Intelligence is the country's main home on this site for work on large language models, factuality and benchmarks. New York University Abu Dhabi holds the Arabic computational linguistics line: morphology, parsing, orthography, grammatical error correction and toolkits.

The Technology Innovation Institute appears through two works. One is Falcon. The other is the 2026 [QIMMA study of Arabic benchmark reliability](https://md.research.elamur.ai/free/en/papers/alqadi-2026-arabic-benchmarks-reliable-qimma-s/), which puts quality checks before evaluation.

The Inception Institute of Artificial Intelligence shares Jais and also offers:

a dual-channel framework for detecting sarcasm through sentiment conflict; - a [large and diverse Arabic corpus for language modeling](https://md.research.elamur.ai/free/en/papers/ali-2022-large-diverse-arabic-corpus-language/); - a 2025 study of [language and planning in robotic navigation](https://md.research.elamur.ai/free/en/papers/mansour-2025-language-planning-robotic-navigation-multilingual/), in which the visual scene is turned into text so a model can reason about its next move.

The University of Sharjah's works cover several subjects:

Arabic sentiment classifiers; - fake news detection; - multilingual explainable detoxification; - the [ArzEn-MultiGenre](https://md.research.elamur.ai/free/en/papers/al-sabbagh-2025-arzen-multigenre-aligned-parallel-dataset/) Egyptian Arabic–English corpus; - a phonology study of malapropisms, published as [Supremacy of suprasegmentals in Arabic phonology](https://md.research.elamur.ai/free/en/papers/guba-2023-supremacy-suprasegmentals-arabic-phonology-evidence/).

United Arab Emirates University contributes the Emirati Arabic verb study, [Rethinking templates](https://md.research.elamur.ai/free/en/papers/kaabi-2019-rethinking-templates-syntactic-analysis-verbal/), and an analysis of control structures in Amharic.

Zayed University's recent works are [Bulbul](https://md.research.elamur.ai/free/en/papers/ashraf-2026-bulbul-dataset-dialectal-arabic-speech/), a dataset for dialectal Arabic speech recognition, and a study of curriculum learning and pseudo-labelling for multi-label dialect identification. Its people on this site include Amr Keleg and Ali Mekky.

### Collaborations

The clearest link between institutions in the country is Jais and Jais-chat. It is shared by Mohamed bin Zayed University of Artificial Intelligence and the Inception Institute of Artificial Intelligence. Some people also connect institutions: Fahad Shahbaz Khan appears among the people of both the Inception Institute and Zayed University. More broadly, Arabic dialects, Arabic corpora and Arabic benchmarks link several institutions, from New York University Abu Dhabi and Mohamed bin Zayed University of Artificial Intelligence to Zayed University, the University of Sharjah and the Technology Innovation Institute.

Beyond the country, the works here show many international author groups:

The CoNLL 2017 shared task and the Arabic Universal Dependencies paper were written with Daniel Zeman and the wider dependency-parsing community. - UniMorph 4.0 joined Salam Khalifa with Khuyagbaatar Batsuren, Omer Goldman and many others. - The factuality paper brought Timothy Baldwin together with Isabelle Augenstein and Meeyoung Cha. - The multitask finetuning work, Humanity's Last Exam and TrustLLM are large multi-institution efforts in which the country's researchers appear among many co-authors.

In the Falcon and QIMMA work, the Technology Innovation Institute connects applied institute research with open model releases and evaluation that the universities also pursue.

### Timeline

From 2015 to 2016, the country's presence here consists of Arabic diacritization and parsing work at New York University Abu Dhabi.

From 2017 to 2019 came:

neural morphological disambiguation; - the Arabic Universal Dependencies treebank; - the CoNLL multilingual parsing task; - the CALIMA Star analyzer; - dialect orthography guidelines; - noise-robust dialect modelling; - theoretical syntax at United Arab Emirates University.

From 2020 to 2021, CAMeL Tools and joint morphological models appeared, along with Arabic error-type annotation and the first Sharjah study on Arabic sentiment.

In 2022 the language-model line began, with crosslingual multitask finetuning and RLPrompt. The same year brought UniMorph 4.0, Arabic fake news detection, the Inception Institute's sarcasm framework and its Arabic corpus.

2023 was the busiest year among the works here. It brought Falcon, Jais, document-level translation, the factuality paper, misinformation pollution, DetectLLM, Physics of Language Models, TARJAMAT, Arabic error correction and the malapropism study.

In 2024, TrustLLM, ArabicMMLU and ArzEn-MultiGenre appeared. In 2025 came Humanity's Last Exam, multilingual detoxification and robotic navigation. The most recent works, from 2026, return to Arabic: QIMMA's audit of Arabic benchmarks, the Bulbul speech dataset and multi-label dialect identification.

## Where

## Agglomerations (3)

1. [**Abu Dhabi**5 institutions*5,777 citations*](https://md.research.elamur.ai/free/en/agglomerations/abu-dhabi/)
2. [**Dubai**1 institution*152 citations*](https://md.research.elamur.ai/free/en/agglomerations/dubai/)
3. [**Al Ain**1 institution*13 citations*](https://md.research.elamur.ai/free/en/agglomerations/al-ain/)

## Institutions (7)

### 🎓 Universities (5)

1. **[New York University Abu Dhabi](https://md.research.elamur.ai/free/en/universities/new-york-university-abu-dhabi/)**University · [Abu Dhabi](https://md.research.elamur.ai/free/en/agglomerations/abu-dhabi/), United Arab Emirates*45 works · 2,055 citations*
2. **[Mohamed bin Zayed University of Artificial Intelligence](https://md.research.elamur.ai/free/en/universities/mohamed-bin-zayed-university-of-artificial-intelligence/)**University · [Abu Dhabi](https://md.research.elamur.ai/free/en/agglomerations/abu-dhabi/), United Arab Emirates*33 works · 3,016 citations*
3. **[University of Sharjah](https://md.research.elamur.ai/free/en/universities/university-of-sharjah/)**University · [Sharjah](https://md.research.elamur.ai/free/en/agglomerations/dubai/), United Arab Emirates*5 works · 152 citations*
4. **[United Arab Emirates University](https://md.research.elamur.ai/free/en/universities/united-arab-emirates-university/)**University · [Al Ain](https://md.research.elamur.ai/free/en/agglomerations/al-ain/), United Arab Emirates*2 works · 13 citations*
5. **[Zayed University](https://md.research.elamur.ai/free/en/universities/zayed-university/)**University · [Abu Dhabi](https://md.research.elamur.ai/free/en/agglomerations/abu-dhabi/), United Arab Emirates*2 works · 1 citation*

### 🔬 Labs and research institutes (2)

1. **[Technology Innovation Institute](https://md.research.elamur.ai/free/en/labs/technology-innovation-institute/)**Research institute · [Abu Dhabi](https://md.research.elamur.ai/free/en/agglomerations/abu-dhabi/), United Arab Emirates*2 works · 436 citations*
2. **[Inception Institute of Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/inception-institute-of-artificial-intelligence/)**Research institute · [Abu Dhabi](https://md.research.elamur.ai/free/en/agglomerations/abu-dhabi/), United Arab Emirates*4 works · 269 citations*

## People (56)

Authors with a page confirmed at its institutions, the most cited first.

1. [**Preslav Nakov**Mohamed bin Zayed University of Artificial Intelligence*32 papers here · 13,932 citations*](https://md.research.elamur.ai/free/en/authors/preslav-nakov/)
2. [**Nizar Habash**New York University Abu Dhabi*80 papers here · 12,659 citations*](https://md.research.elamur.ai/free/en/authors/nizar-habash/)
3. [**Timothy Baldwin**Mohamed bin Zayed University of Artificial Intelligence*26 papers here · 10,796 citations*](https://md.research.elamur.ai/free/en/authors/timothy-baldwin/)
4. [**Yuanzhi Li**Mohamed bin Zayed University of Artificial Intelligence*7 papers here · 6,432 citations*](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/)
5. [**Eric Xing**Mohamed bin Zayed University of Artificial Intelligence*7 papers here · 4,061 citations*](https://md.research.elamur.ai/free/en/authors/eric-xing/)
6. [**Alham Fikri Aji**Mohamed bin Zayed University of Artificial Intelligence*4 papers here · 2,935 citations*](https://md.research.elamur.ai/free/en/authors/alham-fikri-aji/)
7. [**Kentaro Inui**Mohamed bin Zayed University of Artificial Intelligence*8 papers here · 1,877 citations*](https://md.research.elamur.ai/free/en/authors/kentaro-inui/)
8. [**Xiaodan Liang**Mohamed bin Zayed University of Artificial Intelligence*3 papers here · 1,703 citations*](https://md.research.elamur.ai/free/en/authors/xiaodan-liang/)
9. [**AbdelRahim Elmadany**Mohamed bin Zayed University of Artificial Intelligence*6 papers here · 1,560 citations*](https://md.research.elamur.ai/free/en/authors/abdelrahim-elmadany/)
10. [**Thamar Solorio**Mohamed bin Zayed University of Artificial Intelligence*5 papers here · 1,535 citations*](https://md.research.elamur.ai/free/en/authors/thamar-solorio/)
11. [**Salam Khalifa**New York University Abu Dhabi*18 papers here · 1,442 citations*](https://md.research.elamur.ai/free/en/authors/salam-khalifa/)
12. [**Fajri Koto**Mohamed bin Zayed University of Artificial Intelligence*5 papers here · 1,357 citations*](https://md.research.elamur.ai/free/en/authors/fajri-koto/)
13. [**Ossama Obeid**New York University Abu Dhabi*5 papers here · 1,348 citations*](https://md.research.elamur.ai/free/en/authors/ossama-obeid/)
14. [**Zhengzhong Liu**Mohamed bin Zayed University of Artificial Intelligence*5 papers here · 1,215 citations*](https://md.research.elamur.ai/free/en/authors/zhengzhong-liu/)
15. [**Dima Taji**New York University Abu Dhabi*7 papers here · 1,118 citations*](https://md.research.elamur.ai/free/en/authors/dima-taji/)
16. [**Haonan Li**Mohamed bin Zayed University of Artificial Intelligence*3 papers here · 1,111 citations*](https://md.research.elamur.ai/free/en/authors/haonan-li/)
17. [**Fadhl Eryani**New York University Abu Dhabi*5 papers here · 957 citations*](https://md.research.elamur.ai/free/en/authors/fadhl-eryani/)
18. [**Bashar Alhafni**New York University Abu Dhabi*14 papers here · 912 citations*](https://md.research.elamur.ai/free/en/authors/bashar-alhafni/)
19. [**Alexander Erdmann**New York University Abu Dhabi*3 papers here · 854 citations*](https://md.research.elamur.ai/free/en/authors/alexander-erdmann/)
20. [**Nasser Zalmout**New York University Abu Dhabi*7 papers here · 819 citations*](https://md.research.elamur.ai/free/en/authors/nasser-zalmout/)
21. [**Salman Khan**Mohamed bin Zayed University of Artificial Intelligence*3 papers here · 726 citations*](https://md.research.elamur.ai/free/en/authors/salman-khan/)
22. [**Fahad Shahbaz Khan**Mohamed bin Zayed University of Artificial Intelligence*2 papers here · 693 citations*](https://md.research.elamur.ai/free/en/authors/fahad-shahbaz-khan/)
23. [**Sunil Kumar Sahu**Inception Institute of Artificial Intelligence*2 papers here · 536 citations*](https://md.research.elamur.ai/free/en/authors/sunil-kumar-sahu/)
24. [**Hamza Alobeidli**Technology Innovation Institute*2 papers here · 490 citations*](https://md.research.elamur.ai/free/en/authors/hamza-alobeidli/)
25. [**Tatsuki Kuribayashi**Mohamed bin Zayed University of Artificial Intelligence*3 papers here · 395 citations*](https://md.research.elamur.ai/free/en/authors/tatsuki-kuribayashi/)

[See all 56 people →](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/people/)

## Works in our library (81)

Works of its institutions, the most cited first.

1. [**Crosslingual Generalization through Multitask Finetuning**Niklas Muennighoff, Thomas Wang, Lintang Sutawika, et al.*2022 · 692 citations*](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-crosslingual-generalization-through-multitask-finetuning/)
2. [**CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies**Daniel Zeman, Martin Popel, Milan Straka, et al.*2017 · 604 citations*](https://md.research.elamur.ai/free/en/papers/zeman-2017-conll-2017-shared-task-multilingual/)
3. [**The Falcon Series of Open Language Models**Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Alshamsi, et al.*2023 · 436 citations*](https://md.research.elamur.ai/free/en/papers/almazrouei-2023-falcon-series-open-language-models/)
4. [**RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning**Mingkai Deng, Jianyu Wang, Cheng-Ping Hsieh, et al.*2022 · 327 citations*](https://md.research.elamur.ai/free/en/papers/deng-2022-rlprompt-optimizing-discrete-text-prompts/)
5. [**Document-Level Machine Translation with Large Language Models**Longyue Wang, Chenyang Lyu, Tianbo Ji, et al.*2023 · 295 citations*](https://md.research.elamur.ai/free/en/papers/wang-2023-document-level-machine-translation-large/)
6. [**CAMeL Tools: An Open Source Python Toolkit for Arabic Natural Language Processing**Ossama Obeid, Nasser Zalmout, Salam Khalifa, et al.*2020 · 288 citations*](https://md.research.elamur.ai/free/en/papers/obeid-2020-camel-tools-open-source-python/)
7. [**Factuality Challenges in the Era of Large Language Models**Isabelle Augenstein, Timothy Baldwin, Meeyoung Cha, et al.*2023 · 241 citations*](https://md.research.elamur.ai/free/en/papers/augenstein-2023-factuality-challenges-era-large-language/)
8. [**Humanity's Last Exam**Long Phan, Alice Gatti, Ziwen Han, et al.*2025 · 235 citations*](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/)
9. [**TrustLLM: Trustworthiness in Large Language Models**Yue Huang, Lichao Sun, Haoran Wang, et al.*2024 · 226 citations*](https://md.research.elamur.ai/free/en/papers/huang-2024-trustllm-trustworthiness-large-language-models/)
10. [**Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models**Neha Sengupta, Sunil Kumar Sahu, Bokang Jia, et al.*2023 · 217 citations*](https://md.research.elamur.ai/free/en/papers/sengupta-2023-jais-jais-chat-arabic-centric/)
11. [**On the Risk of Misinformation Pollution with Large Language Models**Yikang Pan, Liangming Pan, Wenhu Chen, et al.*2023 · 177 citations*](https://md.research.elamur.ai/free/en/papers/pan-2023-risk-misinformation-pollution-large-language/)
12. [**DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text**Jinyan Su, Terry Zhuo, Di Wang, et al.*2023 · 172 citations*](https://md.research.elamur.ai/free/en/papers/su-2023-detectllm-leveraging-log-rank-information/)
13. [**Unified Guidelines and Resources for Arabic Dialect Orthography**Nizar Habash, Fadhl Eryani, Salam Khalifa, et al.*2018 · 117 citations*](https://md.research.elamur.ai/free/en/papers/habash-2018-unified-guidelines-resources-arabic-dialect/)
14. [**ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic**Fajri Koto, Haonan Li, Sara Shatnawi, et al.*2024 · 116 citations*](https://md.research.elamur.ai/free/en/papers/koto-2024-arabicmmlu-assessing-massive-multitask-language/)
15. [**Physics of Language Models: Part 3.1, Knowledge Storage and Extraction**Zeyuan Allen-Zhu, Yuanzhi Li*2023 · 107 citations*](https://md.research.elamur.ai/free/en/papers/allen-zhu-2023-physics-language-models-part-3/)
16. [**Don't Throw Those Morphological Analyzers Away Just Yet: Neural Morphological Disambiguation for Arabic**Nasser Zalmout, Nizar Habash*2017 · 96 citations*](https://md.research.elamur.ai/free/en/papers/zalmout-2017-don-t-throw-those-morphological/)
17. [**Arabic Fake News Detection Based on Deep Contextualized Embedding Models**Ali Bou Nassif, Ashraf Elnagar, Omar Elgendy, et al.*2022 · 90 citations*](https://md.research.elamur.ai/free/en/papers/nassif-2022-arabic-fake-news-detection-based/)
18. [**UniMorph 4.0: Universal Morphology**Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa*2022 · 82 citations*](https://md.research.elamur.ai/free/en/papers/batsuren-2022-unimorph-4/)
19. [**TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties**Karima Kadaoui, Samar M. Magdy, Abdul Waheed, et al.*2023 · 60 citations*](https://md.research.elamur.ai/free/en/papers/kadaoui-2023-tarjamat-evaluation-bard-chatgpt-machine/)
20. [**Improving Arabic Diacritization through Syntactic Analysis**Anas Shahrour, Salam Khalifa, Nizar Habash*2015 · 58 citations*](https://md.research.elamur.ai/free/en/papers/shahrour-2015-improving-arabic-diacritization-through-syntactic/)
21. [**Universal Dependencies for Arabic**Dima Taji, Nizar Habash, Daniel Zeman*2017 · 52 citations*](https://md.research.elamur.ai/free/en/papers/taji-2017-universal-dependencies-arabic/)
22. [**An Arabic Morphological Analyzer and Generator with Copious Features**Dima Taji, Salam Khalifa, Ossama Obeid, et al.*2018 · 52 citations*](https://md.research.elamur.ai/free/en/papers/taji-2018-arabic-morphological-analyzer-generator-copious/)
23. [**CamelParser: A system for Arabic Syntactic Analysis and Morphological Disambiguation**Anas Shahrour, Salam Khalifa, Dima Taji, et al.*2016 · 44 citations*](https://md.research.elamur.ai/free/en/papers/shahrour-2016-camelparser-system-arabic-syntactic-analysis/)
24. [**Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging**Nasser Zalmout, Nizar Habash*2020 · 44 citations*](https://md.research.elamur.ai/free/en/papers/zalmout-2020-joint-diacritization-lemmatization-normalization-fine/)
25. [**Noise-Robust Morphological Disambiguation for Dialectal Arabic**Nasser Zalmout, Alexander Erdmann, Nizar Habash*2018 · 42 citations*](https://md.research.elamur.ai/free/en/papers/zalmout-2018-noise-robust-morphological-disambiguation-dialectal/)

[See all 81 works →](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/works/)

## Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

💡 Concepts 2[Universal Dependencies · 1 work](https://md.research.elamur.ai/free/en/concepts/universal-dependencies/) · [Corpus linguistics · 1 work](https://md.research.elamur.ai/free/en/concepts/corpus-linguistics/)

📚 Shelves 8[Linguistics & languages · 65 works](https://md.research.elamur.ai/free/en/shelves/linguistics/) · [Natural language processing · 24 works](https://md.research.elamur.ai/free/en/shelves/nlp/) · [Other · 4 works](https://md.research.elamur.ai/free/en/shelves/other/) · [Semitic languages · 25 works](https://md.research.elamur.ai/free/en/shelves/sem/) · [AI & machine learning · 2 works](https://md.research.elamur.ai/free/en/shelves/ai/) · [English · 2 works](https://md.research.elamur.ai/free/en/shelves/en/) · [Mathematics & statistics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/) · [Machine translation · 5 works](https://md.research.elamur.ai/free/en/shelves/machine-translation/)

🧭 Topics 19[Semitic languages · 64 works](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · [Language models & pretraining · 14 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Morphology · 18 works](https://md.research.elamur.ai/free/en/topics/morphology/) · [Multilingual & cross-lingual NLP · 4 works](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Machine translation · 5 works](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Universal Dependencies · 3 works](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) · [Sentiment & emotion · 4 works](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Bias, fairness & safety · 1 work](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Evaluation & benchmarks · 9 works](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Grammatical error correction & learner language · 3 works](https://md.research.elamur.ai/free/en/topics/grammatical-error-correction/) · [Coreference resolution · 1 work](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) · [Treebanks · 1 work](https://md.research.elamur.ai/free/en/topics/treebanks/) · [Implicature · 1 work](https://md.research.elamur.ai/free/en/topics/implicature/) · [Dependency parsing · 2 works](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) · [Tokenization & segmentation · 3 works](https://md.research.elamur.ai/free/en/topics/tokenization/)+4 more

## Works by year

### 2020s

[**2026** 16 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2026/) · [**2025** 9 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2025/) · [**2024** 5 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2024/) · [**2023** 16 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2023/) · [**2022** 13 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2022/) · [**2021** 2 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2021/) · [**2020** 4 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2020/)

### 2010s

[**2019** 3 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2019/) · [**2018** 4 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2018/) · [**2017** 4 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2017/) · [**2016** 4 works](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/year/2016/) · [**2015** 1 work](https://md.research.elamur.ai/free/en/papers/shahrour-2015-improving-arabic-diacritization-through-syntactic/)

- [← back to](https://md.research.elamur.ai/free/en/countries/) — countries

Updated 23 October 2026