---
title: "Qayyem — paper by Elbahnasawi et al. (2026)"
description: "The authors built Qayyem, a web platform that the paper presents as the first cross-prompt, multi-trait Arabic AES system. 18 references."
authors: ["Hoor Tamer Elbahnasawi", "Marwan Sayed", "Sohaila Eltanbouly", "Fatima Zahra Brahamia", "Tamer Elsayed"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)"
source: "https://aclanthology.org/2026.acl-demo.53/"
doi: "10.18653/v1/2026.acl-demo.53"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/elbahnasawi-2026-qayyem-real-time-platform-scoring/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/elbahnasawi-2026-qayyem-real-time-platform-scoring/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/40/) / Qayyem: A Real-time Platform for Scoring Proficiency of Arabic Essays

# Qayyem: A Real-time Platform for Scoring Proficiency of Arabic Essays

**Authors:** Hoor Tamer Elbahnasawi, [Marwan Sayed](https://md.research.elamur.ai/free/en/authors/marwan-sayed/), [Sohaila Eltanbouly](https://md.research.elamur.ai/free/en/authors/sohaila-eltanbouly/), Fatima Zahra Brahamia and [Tamer Elsayed](https://md.research.elamur.ai/free/en/authors/tamer-elsayed/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-demo.53/) · [PDF](https://aclanthology.org/2026.acl-demo.53.pdf) · [DOI 10.18653/v1/2026.acl-demo.53](https://doi.org/10.18653/v1/2026.acl-demo.53) · [OpenAlex](https://openalex.org/W7166829185)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Arabic automated essay scoring (AES) has had few usable tools. Annotated data is scarce, and the only previously deployed system, ARWI, scores essays for one prompt at a time and gives no per-trait scores. The authors built Qayyem, a web platform that the paper presents as the first cross-prompt, multi-trait Arabic AES system. Instructors can write prompts and reusable rubrics, set up assignments, upload essays in batches, pick a scoring model for each trait, get scores in real time, and then review or correct them. A separate scoring server exposes the models through a public API. All five deployed models were trained cross-prompt on LAILA, the largest multi-trait Arabic AES corpus: three feature-based models (RF, NN, XGB), MOOSE, and TRATES. Evaluation uses QWK. TRATES scores best on every trait, but it takes about 30 seconds per essay, while the feature-based models take under a second. The platform makes that speed–accuracy trade-off visible, so users can choose a model to fit their needs. Because the models are cross-prompt, new assignments can be scored without retraining.

## Key points
- LAILA contains 7,859 essays from students in grades 10–12, written for 8 prompts (5 persuasive, 3 explanatory). Each essay is scored on 7 traits: REL (0–2), and ORG, VOC, STY, DEV, MEC and GRM (each 0–5). The holistic score (HOL) is the sum of the trait scores.
- Average QWK across traits:
  - TRATES: 0.653
  - MOOSE: 0.597
  - XGB: 0.593
  - RF: 0.581
  - NN: 0.574
- On relevance, TRATES reaches 0.557 against 0.411 for MOOSE.
- Inference time per essay:
  - NN and XGB: about 0.2 s
  - RF: about 0.3 s
  - MOOSE: about 1 s
  - TRATES: about 30 s, because it makes a separate LLM call for each trait (Fanar in this adaptation).
- MOOSE combines a mixture of experts, pairwise essay ranking and an essay–prompt relevance component, using an AraBERT encoder.
- The software stack has two parts:
  - The assignment manager uses Next.js, PostgreSQL and Prisma.
  - The scoring server uses FastAPI and is configured through files that list which models to load.

## Interesting ideas
- **Per-trait model choice with visible cost.** Each trait gets its own model, a short description, a 0–5 star rating and a performance-based default, so users trade accuracy for speed knowingly rather than blindly.
- **Effectiveness plotted against inference time as a core result.** Reporting quality against per-item cost keeps an expensive LLM-based method from looking best by default.
- **Independent, traceable scoring runs.** Every scoring run with a different model is stored separately and can be compared, deleted or manually corrected later.
- **Cross-prompt evaluation as the default setting.** Models are always tested on prompts they never saw, which gives a more realistic picture of how they will generalize.
- **Rubrics as reusable objects separate from prompts.** The scoring criteria are stored independently of the task text, so the same criteria can be applied to new tasks.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (tree): Let each pipeline stage expose both the perceptron parser and gparse, with a measured LAS/latency rating, and pick a sensible default per use case.
- **I2** (learn): Report every evaluation as accuracy against cost per sentence, especially when deciding whether to use LLM teacher tiers or cheaper silver-data witnesses.
- **I3** (learn): Keep each witness parser's output as a versioned run, so disagreements and human fixes can be traced and turned into repair rules.
- **I4** (answer): Evaluate the readers on held-out fable collections or course topics never used during development, so they cannot overfit to familiar texts.
- **I5** (answer): Store answer-checking criteria for school tests apart from the question texts, so a new question can reuse an existing rubric.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Qatar University](https://md.research.elamur.ai/free/en/universities/qatar-university/) — University, Doha, Qatar · 48 works · 1,026 citations

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works · [🎓 Education](https://md.research.elamur.ai/free/en/shelves/social-sciences/education/) · 203 works

🧭 Topics (1): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works

## Cite

Cite as: Hoor Tamer Elbahnasawi, Marwan Sayed, Sohaila Eltanbouly, Fatima Zahra Brahamia and Tamer Elsayed. 2026. Qayyem: A Real-time Platform for Scoring Proficiency of Arabic Essays. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{elbahnasawi2026qayyem,
  title = {{Qayyem: A Real-time Platform for Scoring Proficiency of Arabic Essays}},
  author = {Hoor Tamer Elbahnasawi, Marwan Sayed, Sohaila Eltanbouly, Fatima Zahra Brahamia and Tamer Elsayed},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-demo.53},
  url = {https://doi.org/10.18653/v1/2026.acl-demo.53}
}
```

- [← previous QAMAR: A New Fully Verified and Accurate Quranic Arabic Morphological Analysis Resource.](https://md.research.elamur.ai/free/en/papers/faqihi-2026-qamar-new-fully-verified-accurate/)
- [next → QFinZero: A Unified Financial Toolchain for LLM-Based Trading Agents](https://md.research.elamur.ai/free/en/papers/luo-2026-qfinzero-unified-financial-toolchain-llm/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/40/)

## References

18 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abeer Alqahtani and Amal Alsaif. 2020. [Automated Arabic essay evaluation](https://md.research.elamur.ai/free/en/papers/alqahtani-2020-automated-arabic-essay-evaluation/). In Proceedings of the 17th International Conference on Natural Language Processing (ICON), pages 181–190, Indian Institute of Technology Patna, Patna, India. NLP Association of India (NLPAI).
2. Waleed Alsanie, Mohamed I Alkanhal, Mohammed Al-hamadi, and Abdulaziz O Alqabbany. 2022. Automatic scoring of Arabic essays over three linguistic levels. Progress in Artificial Intelligence, pages 1– 13. [↗](https://doi.org/10.1007/s13748-021-00257-z)
3. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. [AraBERT: Transformer-based model for Arabic language understanding](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/). In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9–15, Marseille, France. European Language Resources Association. [↗](https://doi.org/10.48550/arxiv.2003.00104)
4. May Bashendy, Walid Massoud, Sohaila Eltanbouly, Salam Albatarni, Marwan Sayed, Abrar Abir, Houda Bouamor, and Tamer Elsayed. 2026. [LAILA: A large trait-based dataset for Arabic automated essay scoring](https://md.research.elamur.ai/free/en/papers/bashendy-2026-laila-large-trait-based-dataset/). In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026). Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2512.24235)
5. Jill Burstein, Martin Chodorow, and Claudia Leacock. 2003. Criterionsm online essay evaluation: An application for automated evaluation of student essays. In Proceedings of the Fifteenth Annual Conference on Innovative Applications of Artificial Intelligence (IAAI), pages 3–10. Association for the Advancement of Artificial Intelligence. Reposted with permission on ETS.org. [find](https://scholar.google.com/scholar?q=Jill+Burstein%2C+Martin+Chodorow%2C+and+Claudia+Leacock%2E+2003%2E+Criterionsm+online+essay+evaluation%3A+An+application+for+automated+evaluation+of+student+essays%2E+In+Proceedings+of+the+Fifteenth+Annual+Confer)
6. Kumar Satvik Chaudhary, Chengshuai Zhao, Fan Zhang, Yung Hin Tse, Garima Agrawal, Yuli Deng, and Huan Liu. 2025. EssayCBM: Rubric-aligned concept bottleneck models for transparent essay grading. arXiv preprint arXiv:2512.20817. [↗](https://arxiv.org/abs/2512.20817)
7. Jacob Cohen. 1968. Weighted kappa: nominal scale agreement provision for scaled disagreement or partial credit. Psychological bulletin, 70(4):213. [↗](https://doi.org/10.1037/h0026256)
8. Fei Dong, Yue Zhang, and Jie Yang. 2017. [Attention-based recurrent convolutional neural network for automatic essay scoring](https://md.research.elamur.ai/free/en/papers/dong-2017-attention-based-recurrent-convolutional-neural/). In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 153–162, Vancouver, Canada. Association for Computational Linguistics.
9. Sohaila Eltanbouly, Salam Albatarni, and Tamer Elsayed. 2025. TRATES: Trait-specific rubric-assisted cross-prompt essay scoring. In Findings of the Association for Computational Linguistics: ACL 2025, pages 20528–20543, Vienna, Austria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sohaila+Eltanbouly%2C+Salam+Albatarni%2C+and+Tamer+Elsayed%2E+2025%2E+TRATES%3A+Trait%2Dspecific+rubric%2Dassisted+cross%2Dprompt+essay+scoring%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2025%2C)
10. Rayed Ghazawi and Edwin Simpson. 2024. [Automated essay scoring in Arabic: a dataset and analysis of a BERT-based system](https://md.research.elamur.ai/free/en/papers/ghazawi-2024-automated-essay-scoring-arabic-dataset/). arXiv preprint arXiv:2407.11212. [↗](https://arxiv.org/abs/2407.11212)
11. Rayed Ghazawi and Edwin Simpson. 2025. [How well can LLMs grade essays in Arabic?](https://md.research.elamur.ai/free/en/papers/ghazawi-2025-well-llms-grade-essays-arabic/) Computers and Education: Artificial Intelligence, page 100449. [↗](https://doi.org/10.1016/j.caeai.2025.100449)
12. Jiefu Gong, Xiao Hu, Wei Song, Ruiji Fu, Zhichao Sheng, Bo Zhu, Shijin Wang, and Ting Liu. 2021. IFlyEA: A Chinese essay assessment system with automated rating, review generation, and recommendation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations, pages 240–248, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jiefu+Gong%2C+Xiao+Hu%2C+Wei+Song%2C+Ruiji+Fu%2C+Zhichao+Sheng%2C+Bo+Zhu%2C+Shijin+Wang%2C+and+Ting+Liu%2E+2021%2E+IFlyEA%3A+A+Chinese+essay+assessment+system+with+automated+rating%2C+review+generation%2C+and+recommendation%2E)
13. Reo Hirao, Mio Arai, Hiroki Shimanaka, Satoru Katsumata, and Mamoru Komachi. 2020. Automated essay scoring system for nonnative Japanese learners. In Proceedings of the Twelfth Language Resources and Evaluation Conference (LREC 2020), pages 1250–1257, Marseille, France. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Reo+Hirao%2C+Mio+Arai%2C+Hiroki+Shimanaka%2C+Satoru+Katsumata%2C+and+Mamoru+Komachi%2E+2020%2E+Automated+essay+scoring+system+for+nonnative+Japanese+learners%2E+In+Proceedings+of+the+Twelfth+Language+Resources+and+)
14. Rahul Kumar, Sandeep Mathias, Sriparna Saha, and Pushpak Bhattacharyya. 2022. Many hands make light work: Using essay traits to automatically score essays. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1485–1495, Seattle, United States. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2102.00781)
15. Shengjie Li and Vincent Ng. 2024. Conundrums in cross-prompt automated essay scoring: Making sense of the state of the art. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7661– 7681, Bangkok, Thailand. Association for Computational Linguistics. [↗](https://doi.org/10.48448/4gz2-vw60)
16. Zhexiong Liu, Diane Litman, Elaine L Wang, Tianwen Li, Mason Gobat, Lindsay Clare Matsumura, and Richard Correnti. 2025. [eRevise+RF: A writing evaluation system for assessing student essay revisions and providing formative feedback](https://md.research.elamur.ai/free/en/papers/abbas-2025-fanar-arabic-centric-multimodal-generative/). In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations), pages 173–190, Albuquerque, New Mexico. Association for Computational Linguistics. An Arabic-centric multimodal generative ai platform. arXiv preprint arXiv:2501.13944. [↗](https://arxiv.org/abs/2501.13944)
17. Jiayi Xie, Kaiwei Cai, Li Kong, Junsheng Zhou, and Weiguang Qu. 2022. Automated essay scoring via pairwise contrastive regression. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2724–2733, Gyeongju, Republic of Korea. International Committee on Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jiayi+Xie%2C+Kaiwei+Cai%2C+Li+Kong%2C+Junsheng+Zhou%2C+and+Weiguang+Qu%2E+2022%2E+Automated+essay+scoring+via+pairwise+contrastive+regression%2E+In+Proceedings+of+the+29th+International+Conference+on+Computational+)
18. Chunyun Zhang, Jiqin Deng, Xiaolin Dong, Hongyan Zhao, Kailin Liu, and Chaoran Cui. 2025. Pairwise dual-level alignment for cross-prompt automated essay scoring. Expert Systems with Applications, 265:125924. A [↗](https://doi.org/10.1016/j.eswa.2024.125924)

*Updated 1 November 2026*