---
title: "Arabic Large Language Models for Medical Text Generation — Allam 2025"
description: "The paper looks at Arabic medical text generation, where informal patient questions in many dialects… 68.5% recall. 28 references, cited by 5 papers here."
authors: ["Abdulrahman Allam", "Seif Ahmed", "Ali Hamdi", "Ammar Mohammed"]
year: 2025
venue: "arXiv:2509.10095"
source: "https://arxiv.org/abs/2509.10095"
doi: "10.48550/arxiv.2509.10095"
arxiv: "2509.10095"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/allam-2025-arabic-large-language-models-medical/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/allam-2025-arabic-large-language-models-medical/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/2/) / Arabic Large Language Models for Medical Text Generation

# Arabic Large Language Models for Medical Text Generation

**Authors:** [Abdulrahman Allam](https://md.research.elamur.ai/free/en/authors/abdulrahman-allam/), [Seif Ahmed](https://md.research.elamur.ai/free/en/authors/seif-ahmed/), [Ali Hamdi](https://md.research.elamur.ai/free/en/authors/ali-hamdi/) and [Ammar Mohammed](https://md.research.elamur.ai/free/en/authors/ammar-mohammed/) · **Year:** 2025 · **Venue:** arXiv:2509.10095 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2509.10095) · [PDF](https://arxiv.org/pdf/2509.10095) · [DOI 10.48550/arxiv.2509.10095](https://doi.org/10.48550/arxiv.2509.10095) · [arXiv 2509.10095](https://arxiv.org/abs/2509.10095) · [OpenAlex](https://openalex.org/W4412973250)

**Citations:** 5 citations (OpenAlex, 2026-10-14) · [5](https://md.research.elamur.ai/free/en/papers/allam-2025-arabic-large-language-models-medical/cited-by/) in our library, of the 140,884 papers whose bibliographies we read

## Summary
The paper looks at Arabic medical text generation, where informal patient questions in many dialects and a lack of domain data hold back useful chatbots for healthcare systems. The authors scraped Facebook groups in which doctors answer patients' complaints. They cleaned the posts, normalized dialectal and spelling variation, and kept about 20,000 question–answer pairs. Several pre-trained generators were then adapted with LoRA through Hugging Face Transformers, including Mistral-7B-Instruct-v0.2, LLaMA-2-7B and GPT-2 Medium. Outputs were scored against reference doctor replies with BERTScore and also checked by hand for coherence and relevance. The fine-tuned Mistral-7B scored best, at roughly 68–69% BERTScore precision, recall and F1. The authors argue that exact-match metrics undervalue answers that are correct but worded differently, which is why they add a qualitative review. They also stress that real deployment needs verified medical sources or expert review. The work matters as a dialect-rich, real-world medical dialogue resource for an under-resourced language.

## Key points
- Over 40,000 medical posts were collected from Facebook groups with a Python pipeline using Selenium, BeautifulSoup and Pandas. Adaptive scrolling and pattern-based extraction were used to capture dynamic content.
- Preprocessing involved three steps:
  - noise removal (ads, emojis, incomplete entries);
  - normalization of dialects, spellings and informal phrasing;
  - deduplication, plus regex-based fixes for typos and repeated phrases.
  These steps left about 20,000 QA pairs.
- Candidate models were AraGPT2-Base, Meta-LLaMA/LLaMA-2-7B, BigScience/BLOOM-560M, Mistral-7B-Instruct-v0.2 and OpenAI GPT-2 Medium. All were fine-tuned with LoRA to keep compute costs low.
- The best system was the fine-tuned Mistral-7B, with average BERTScore precision 68.5%, recall 69.08% and F1 68.5%.
- The authors name two open problems: many user queries lack history or symptom detail, and generated advice needs validation against trusted sources or by experts.

## Interesting ideas
- Community threads where qualified people answer laypeople give naturally paired, informal question–answer data with realistic noise, at no annotation cost.
- The authors judge outputs by semantic similarity plus human review, because string overlap penalizes correct paraphrases.
- Dialect and spelling variants are normalized before modeling, so that sparse data is not split across many surface forms.
- The paper treats vague questions with missing context as a core difficulty rather than as noise.
- The authors insist that generated advice be checked against verified sources or experts before it can be trusted.

## For Mova

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

- **I1** (learn): Mova could mine forum-style Q&A threads as silver pairs for its readers, then filter them with witness-parser agreement before using them for training.
- **I2** (back): the text → graph → text compressor could be scored by re-parsing its output and comparing meaning graphs instead of surface strings, with a scrambled-graph negative control.
- **I3** (tokens): Mova could add a normalization layer that maps informal English spellings and contractions to canonical lemmas while keeping the original token, so every step stays explainable.
- **I4** (world): the world builder could mark under-specified states or entities explicitly, so the answer stage can hedge or ask for detail instead of guessing.
- **I5** (learn): Mova could treat LLM-teacher outputs as unverified until a knowledge-graph or rule check confirms them, and track which tier each fact came from.

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

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

Topics: [✍️ Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/) · [🐪 Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/)

## Institutions

- [October University of Modern Sciences and Arts](https://md.research.elamur.ai/free/en/universities/october-university-of-modern-sciences-and-arts/) — University, Cairo, Egypt · 7 works · 25 citations

## Cite

Cite as: Abdulrahman Allam, Seif Ahmed, Ali Hamdi and Ammar Mohammed. 2025. Arabic Large Language Models for Medical Text Generation. arXiv:2509.10095.

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

```bibtex
@misc{allam2025arabic,
  title = {{Arabic Large Language Models for Medical Text Generation}},
  author = {Abdulrahman Allam, Seif Ahmed, Ali Hamdi and Ammar Mohammed},
  year = {2025},
  doi = {10.48550/arxiv.2509.10095},
  eprint = {2509.10095},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2509.10095}
}
```

- [← previous Memorization or Reasoning? Exploring the Idiom Understanding of LLMs](https://md.research.elamur.ai/free/en/papers/kim-2025-memorization-or-reasoning-exploring-idiom/)
- [next → Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?](https://md.research.elamur.ai/free/en/papers/novak-2025-findings-fourth-shared-task-multilingual/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/2/)

## References

28 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. D. E. Detmer, E. B. Steen, and R. S. Dick, “The computer-based patient record: an essential technology for health care,” 1997. [find](https://scholar.google.com/scholar?q=D%2E+E%2E+Detmer%2C+E%2E+B%2E+Steen%2C+and+R%2E+S%2E+Dick%2C+%E2%80%9CThe+computer%2Dbased+patient+record%3A+an+essential+technology+for+health+care%2C%E2%80%9D+1997%2E)
2. T. C. Brown, “The concept of value in resource allocation,” Land economics, vol. 60, no. 3, pp. 231–246, 1984. [find](https://scholar.google.com/scholar?q=T%2E+C%2E+Brown%2C+%E2%80%9CThe+concept+of+value+in+resource+allocation%2C%E2%80%9D+Land+economics%2C+vol%2E+60%2C+no%2E+3%2C+pp%2E+231%E2%80%93246%2C+1984%2E)
3. M. Rashid and M. Sharma, “Ai-assisted diagnosis and treatment planning—a discussion of how ai can assist healthcare professionals in making more accurate diagnoses and treatment plans for diseases,” AI in Disease Detection: Advancements and Applications, pp. 313–336, 2025. [find](https://scholar.google.com/scholar?q=M%2E+Rashid+and+M%2E+Sharma%2C+%E2%80%9CAi%2Dassisted+diagnosis+and+treatment+planning%E2%80%94a+discussion+of+how+ai+can+assist+healthcare+professionals+in+making+more+accurate+diagnoses+and+treatment+plans+for+diseases%2C%E2%80%9D+A)
4. Z. A. Nazi and W. Peng, “Large language models in healthcare and medical domain: A review,” in Informatics, vol. 11, no. 3. MDPI, 2024, p. 57. [find](https://scholar.google.com/scholar?q=Z%2E+A%2E+Nazi+and+W%2E+Peng%2C+%E2%80%9CLarge+language+models+in+healthcare+and+medical+domain%3A+A+review%2C%E2%80%9D+in+Informatics%2C+vol%2E+11%2C+no%2E+3%2E+MDPI%2C+2024%2C+p%2E+57%2E)
5. C. Peng, X. Yang, A. Chen, K. E. Smith, N. PourNejatian, A. B. Costa, C. Martin, M. G. Flores, Y. Zhang, T. Magoc et al., “A study of generative large language model for medical research and healthcare,” NPJ digital medicine, vol. 6, no. 1, p. 210, 2023. [find](https://scholar.google.com/scholar?q=C%2E+Peng%2C+X%2E+Yang%2C+A%2E+Chen%2C+K%2E+E%2E+Smith%2C+N%2E+PourNejatian%2C+A%2E+B%2E+Costa%2C+C%2E+Martin%2C+M%2E+G%2E+Flores%2C+Y%2E+Zhang%2C+T%2E+Magoc+et+al%2E%2C+%E2%80%9CA+study+of+generative+large+language+model+for+medical+research+and+healthcar)
6. L. A. Salem, T. Shishtawy, N. El-Attar et al., “Enhancing healthcare management: A case study of a medical chatbot in egypt,” Benha Journal of Applied Sciences, vol. 9, no. 5, pp. 199–210, 2024. [find](https://scholar.google.com/scholar?q=L%2E+A%2E+Salem%2C+T%2E+Shishtawy%2C+N%2E+El%2DAttar+et+al%2E%2C+%E2%80%9CEnhancing+healthcare+management%3A+A+case+study+of+a+medical+chatbot+in+egypt%2C%E2%80%9D+Benha+Journal+of+Applied+Sciences%2C+vol%2E+9%2C+no%2E+5%2C+pp%2E+199%E2%80%93210%2C+2024%2E)
7. A. Hamdi, A. A. Mazrou, and M. Shaltout, “Llm-sem: A sentiment-based student engagement metric using llms for e-learning platforms,” arXiv preprint arXiv:2412.13765, 2024. [↗](https://arxiv.org/abs/2412.13765)
8. A. Hamdi, H. Kassab, M. Bahaa, and M. Mohamed, “Riro: Reshaping inputs, refining outputs unlocking the potential of large language models in data-scarce contexts,” arXiv preprint arXiv:2412.15254, 2024. [↗](https://arxiv.org/abs/2412.15254)
9. N. Kühl, M. Schemmer, M. Goutier, and G. Satzger, “Artificial intelligence and machine learning,” Electronic Markets, vol. 32, no. 4, pp. 2235–2244, 2022. [find](https://scholar.google.com/scholar?q=N%2E+Ku%CC%88hl%2C+M%2E+Schemmer%2C+M%2E+Goutier%2C+and+G%2E+Satzger%2C+%E2%80%9CArtificial+intelligence+and+machine+learning%2C%E2%80%9D+Electronic+Markets%2C+vol%2E+32%2C+no%2E+4%2C+pp%2E+2235%E2%80%932244%2C+2022%2E)
10. M. L. PRIYANKA, B. T. R. NAYAKA, B. S. RAKSHITHA, B. VAMSHI, and B. M. K. YADAV, “Hospital management system with chatbot,” International Journal of Mechanical Engineering Research and Technology, vol. 16, no. 2, pp. 144–154, 2024. [find](https://scholar.google.com/scholar?q=M%2E+L%2E+PRIYANKA%2C+B%2E+T%2E+R%2E+NAYAKA%2C+B%2E+S%2E+RAKSHITHA%2C+B%2E+VAMSHI%2C+and+B%2E+M%2E+K%2E+YADAV%2C+%E2%80%9CHospital+management+system+with+chatbot%2C%E2%80%9D+International+Journal+of+Mechanical+Engineering+Research+and+Technology%2C+vol)
11. M. Abdelhay, A. Mohammed, and H. A. Hefny, “Deep learning for arabic healthcare: Medicalbot,” Social Network Analysis and Mining, vol. 13, no. 1, p. 71, 2023. [find](https://scholar.google.com/scholar?q=M%2E+Abdelhay%2C+A%2E+Mohammed%2C+and+H%2E+A%2E+Hefny%2C+%E2%80%9CDeep+learning+for+arabic+healthcare%3A+Medicalbot%2C%E2%80%9D+Social+Network+Analysis+and+Mining%2C+vol%2E+13%2C+no%2E+1%2C+p%2E+71%2C+2023%2E)
12. D. Al-Ghadhban and N. Al-Twairesh, “Nabiha: an arabic dialect chatbot,” International Journal of Advanced Computer Science and Applications, vol. 11, no. 3, 2020. [find](https://scholar.google.com/scholar?q=D%2E+Al%2DGhadhban+and+N%2E+Al%2DTwairesh%2C+%E2%80%9CNabiha%3A+an+arabic+dialect+chatbot%2C%E2%80%9D+International+Journal+of+Advanced+Computer+Science+and+Applications%2C+vol%2E+11%2C+no%2E+3%2C+2020%2E)
13. O. Hosam Abdellaif, A. Nader, and A. Hamdi, “Lmrpa: Large language model-driven efficient robotic process automation for ocr,” arXiv eprints, pp. arXiv–2412, 2024. [find](https://scholar.google.com/scholar?q=O%2E+Hosam+Abdellaif%2C+A%2E+Nader%2C+and+A%2E+Hamdi%2C+%E2%80%9CLmrpa%3A+Large+language+model%2Ddriven+efficient+robotic+process+automation+for+ocr%2C%E2%80%9D+arXiv+eprints%2C+pp%2E+arXiv%E2%80%932412%2C+2024%2E)
14. K. Namee, T. Prempranee, W. Phonngam, R. Kaewsaeng-On, and A. Meny, “Enhancing hospital bed management through chatbots: Integrating dialogflow and firebase cloud messaging for real-time bed availability and reservation system,” in 2024 22nd International Conference on ICT and Knowledge Engineering (ICT&KE). IEEE, 2024, pp. 1–6. [find](https://scholar.google.com/scholar?q=K%2E+Namee%2C+T%2E+Prempranee%2C+W%2E+Phonngam%2C+R%2E+Kaewsaeng%2DOn%2C+and+A%2E+Meny%2C+%E2%80%9CEnhancing+hospital+bed+management+through+chatbots%3A+Integrating+dialogflow+and+firebase+cloud+messaging+for+real%2Dtime+bed+availabil)
15. K. Denecke and W. Nejdl, “How valuable is medical social media data? content analysis of the medical web,” Information Sciences, vol. 179, no. 12, pp. 1870–1880, 2009. [find](https://scholar.google.com/scholar?q=K%2E+Denecke+and+W%2E+Nejdl%2C+%E2%80%9CHow+valuable+is+medical+social+media+data%3F+content+analysis+of+the+medical+web%2C%E2%80%9D+Information+Sciences%2C+vol%2E+179%2C+no%2E+12%2C+pp%2E+1870%E2%80%931880%2C+2009%2E)
16. S. Della Rosa, F. Sen et al., “Health topics on facebook groups: content analysis of posts in multiple sclerosis communities,” Interactive Journal of Medical Research, vol. 8, no. 1, p. e10146, 2019. [find](https://scholar.google.com/scholar?q=S%2E+Della+Rosa%2C+F%2E+Sen+et+al%2E%2C+%E2%80%9CHealth+topics+on+facebook+groups%3A+content+analysis+of+posts+in+multiple+sclerosis+communities%2C%E2%80%9D+Interactive+Journal+of+Medical+Research%2C+vol%2E+8%2C+no%2E+1%2C+p%2E+e10146%2C+2019%2E)
17. O. H. Abdellaif, A. N. Hassan, and A. Hamdi, “Erpa: Efficient rpa model integrating ocr and llms for intelligent document processing,” in 2024 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC). IEEE, 2024, pp. 295–300. [find](https://scholar.google.com/scholar?q=O%2E+H%2E+Abdellaif%2C+A%2E+N%2E+Hassan%2C+and+A%2E+Hamdi%2C+%E2%80%9CErpa%3A+Efficient+rpa+model+integrating+ocr+and+llms+for+intelligent+document+processing%2C%E2%80%9D+in+2024+International+Mobile%2C+Intelligent%2C+and+Ubiquitous+Computi)
18. P. Zhang and M. N. Kamel Boulos, “Generative ai in medicine and healthcare: promises, opportunities and challenges,” Future Internet, vol. 15, no. 9, p. 286, 2023. [find](https://scholar.google.com/scholar?q=P%2E+Zhang+and+M%2E+N%2E+Kamel+Boulos%2C+%E2%80%9CGenerative+ai+in+medicine+and+healthcare%3A+promises%2C+opportunities+and+challenges%2C%E2%80%9D+Future+Internet%2C+vol%2E+15%2C+no%2E+9%2C+p%2E+286%2C+2023%2E)
19. O. H. Abdellaif, A. Nader, and A. Hamdi, “Lmrpa: Large language model-driven efficient robotic process automation for ocr,” arXiv preprint arXiv:2412.18063, 2024. [↗](https://arxiv.org/abs/2412.18063)
20. O. Abdellatif, A. Ayman, and A. Hamdi, “Lmv-rpa: Large model voting-based robotic process automation,” arXiv preprint arXiv:2412.17965, 2024. [↗](https://arxiv.org/abs/2412.17965)
21. A. Rekik, M. Chebbi, and N. Boughanmi, “A medical chatbot for tunisian dialect using a rule-based and machine learning approach,” Journal of Medical Informatics, vol. 12, no. 3, pp. 45–56, 2023. [find](https://scholar.google.com/scholar?q=A%2E+Rekik%2C+M%2E+Chebbi%2C+and+N%2E+Boughanmi%2C+%E2%80%9CA+medical+chatbot+for+tunisian+dialect+using+a+rule%2Dbased+and+machine+learning+approach%2C%E2%80%9D+Journal+of+Medical+Informatics%2C+vol%2E+12%2C+no%2E+3%2C+pp%2E+45%E2%80%9356%2C+2023%2E)
22. L. Wassim, K. Mohamed, and A. Hamdi, “Llm-daas: Llm-driven drone-as-a-service operations from text user requests,” arXiv preprint arXiv:2412.11672, 2024. [↗](https://arxiv.org/abs/2412.11672)
23. R. G. Gamage, K. U. Senadeera, N. S. Bandara, K. Y. Abeywardena, D. D. Diyamullage, and N. Amarasena, “Pharmago: An online pharmaceutical ordering platform,” in 2021 3rd International Conference on Advancements in Computing (ICAC), 2021, pp. 364–370. [find](https://scholar.google.com/scholar?q=R%2E+G%2E+Gamage%2C+K%2E+U%2E+Senadeera%2C+N%2E+S%2E+Bandara%2C+K%2E+Y%2E+Abeywardena%2C+D%2E+D%2E+Diyamullage%2C+and+N%2E+Amarasena%2C+%E2%80%9CPharmago%3A+An+online+pharmaceutical+ordering+platform%2C%E2%80%9D+in+2021+3rd+International+Conference+on+Ad)
24. J. Anwar, P. Nadi, and N. Seddik, “Towards building a chatbot-based first aid service in arabic language,” Journal of Advanced Research in Applied Sciences and Engineering Technology, vol. 45, no. 2, pp. 1–10, 2025. [find](https://scholar.google.com/scholar?q=J%2E+Anwar%2C+P%2E+Nadi%2C+and+N%2E+Seddik%2C+%E2%80%9CTowards+building+a+chatbot%2Dbased+first+aid+service+in+arabic+language%2C%E2%80%9D+Journal+of+Advanced+Research+in+Applied+Sciences+and+Engineering+Technology%2C+vol%2E+45%2C+no%2E+2%2C+)
25. O. Hamad, K. Shaban, and A. Hamdi, “Asem: Enhancing empathy in chatbot through attention-based sentiment and emotion modeling,” in Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, pp. 1588–1601. [find](https://scholar.google.com/scholar?q=O%2E+Hamad%2C+K%2E+Shaban%2C+and+A%2E+Hamdi%2C+%E2%80%9CAsem%3A+Enhancing+empathy+in+chatbot+through+attention%2Dbased+sentiment+and+emotion+modeling%2C%E2%80%9D+in+Proceedings+of+the+2024+Joint+International+Conference+on+Computation)
26. M. Aldea, P. Rolland, S. Simon, A. Poplu, M. Wartelle, B. Vignal, J.-C. Louis, F. Lion, A. Borie, D. Planchard et al., “Using ai to automatically process data from unstructured health records of patients with lung cancer,” Cancer Research, vol. 84, no. 6 Supplement, pp. 3569–3569, 2024. [find](https://scholar.google.com/scholar?q=M%2E+Aldea%2C+P%2E+Rolland%2C+S%2E+Simon%2C+A%2E+Poplu%2C+M%2E+Wartelle%2C+B%2E+Vignal%2C+J%2E%2DC%2E+Louis%2C+F%2E+Lion%2C+A%2E+Borie%2C+D%2E+Planchard+et+al%2E%2C+%E2%80%9CUsing+ai+to+automatically+process+data+from+unstructured+health+records+of+patie)
27. K. Nova, “Generative ai in healthcare: advancements in electronic health records, facilitating medical languages, and personalized patient care,” Journal of Advanced Analytics in Healthcare Management, vol. 7, no. 1, pp. 115–131, 2023. [find](https://scholar.google.com/scholar?q=K%2E+Nova%2C+%E2%80%9CGenerative+ai+in+healthcare%3A+advancements+in+electronic+health+records%2C+facilitating+medical+languages%2C+and+personalized+patient+care%2C%E2%80%9D+Journal+of+Advanced+Analytics+in+Healthcare+Management)
28. S. Khan, A. Saify, S. Gosaliya, D. Jain, and M. J. Zalte, “Medimatch: Ai-driven drug recommendation system,” in 2024 2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS). IEEE, 2024, pp. 1342–1349. [find](https://scholar.google.com/scholar?q=S%2E+Khan%2C+A%2E+Saify%2C+S%2E+Gosaliya%2C+D%2E+Jain%2C+and+M%2E+J%2E+Zalte%2C+%E2%80%9CMedimatch%3A+Ai%2Ddriven+drug+recommendation+system%2C%E2%80%9D+in+2024+2nd+International+Conference+on+Sustainable+Computing+and+Smart+Systems+%28ICSCSS%29%2E+I)