AbjadNLP 2027 · Shared task

AbjadGenEval 2027

AI-generated text detection across Arabic-script languages

Distinguishing human-written from AI-generated text in Modern Standard Arabic, Urdu and Persian, through language-specific and multilingual evaluation tracks.

Explore the task ↓Participation details

Three languages. One detection challenge.

Arabic · MSAاللغة العربية
Urduاردو زبان
Persianزبان فارسی

Illustrative language labels, not evaluation examples.

About the shared task

Detecting AI-generated text

AbjadGenEval invites participants to develop systems that distinguish human-authored from machine-generated text in languages written using Arabic-derived scripts. The task explores detection performance across different linguistic and resource settings.

Track 01

Arabic (MSA)

Binary classification of human-written and AI-generated Modern Standard Arabic text.

Track 02

Urdu

Binary classification of human-written and AI-generated Urdu text.

Track 03

Persian

Binary classification of human-written and AI-generated Persian text.

Track 04

Multilingual Abjad

Develop a unified detection system evaluated across all three languages.

Task format and evaluation

Given a text passage, systems predict a binary label: 0 = human-written or 1 = AI-generated. The previous edition used macro-F1 as its primary evaluation metric and accuracy as a secondary metric. The 2027 protocol will be confirmed by the organisers.

Taking part

Participation details

The 2027 dataset release, registration, evaluation guidance and deadlines will be announced here when confirmed.

See the previous AbjadGenEval website for background. Its 2026 dates and submission instructions do not automatically apply to 2027.

Visit the AbjadNLP 2027 workshop page →
Languages
Arabic (MSA), Urdu, Persian
Data access and licensing
To be announced
2027 evaluation protocol
To be confirmed
Registration and submissions
To be announced
Shared-task dates
To be announced

The team

Shared-task organisers

The previous edition's organising team is shown below; the 2027 team is subject to confirmation.

  • Saad EzziniKing Fahd University of Petroleum & Minerals
  • Irfan AhmedKing Fahd University of Petroleum & Minerals
  • Salmane ChafikMohammed VI Polytechnic University
  • Shadi AbudalfaKing Fahd University of Petroleum & Minerals
  • Mo El-HajVinUniversity
  • Ahmed AbdelaliHUMAIN
  • Mustafa JarrarHamad Bin Khalifa University / Birzeit University
  • Nadir DurraniHamad Bin Khalifa University
  • Hassan SajjadDalhousie University
  • Farah AdeebaUniversity of Massachusetts Amherst