Elamur Research⌕
☰
home / papers / 2026 / Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection

Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection

Paper · 2026 · Chaimae Abouzahir, Musa Khan, Hala Ali-Hassan et al.

Summary

LLMs handle English medical questions much better than Arabic ones, and this is usually blamed on scarce Arabic training data. The authors test that explanation on Mistral-Small-3.2-24B using MedAraBench and a Google-Translate English version of it. They apply tuned lens probing, causal activation patching and a cross-lingual KL divergence profile. The evidence shows the right answer does form in middle-layer Arabic representations but is lost before the output. They describe this as a failure to route knowledge, not missing knowledge. Based on this, they propose TLoRA: LoRA applied only to the layers below the point where English and Arabic representations diverge, plus an alignment loss that uses the model's own English hidden states as an anchor. On multiple-choice medical QA, TLoRA beats full-network LoRA, zero-shot and few-shot baselines. It also keeps generation ability better than broader fine-tuning. The paper releases AraClinicDialog, a clinician-built dialogue benchmark. The broader lesson is that diagnosing a model's internals can tell you where to adapt it.

Key points

  • Zero-shot, Mistral-Small-3.2-24B scores 57.8% on the English version of MedAraBench and 50.8% on the Arabic original. Of the questions it gets right in English, 29.6% fail in Arabic.
  • The chosen adaptation window is L1–34, taken from the mechanistic diagnosis rather than from downstream scores. It beat full-network LoRA and both wider and narrower windows on MCQA.
  • TLoRA lowers the English-right/Arabic-wrong rate from 29.6% to 19.0%, compared with 20.2% for Full LoRA.
  • In CE-only ablations, L1–34 still leads, so the placement of the window matters most. The alignment term mainly improves generation.
  • AraClinicDialog contains 500 clinician-authored hypothetical dialogues in MSA, with validated variants in four dialects. The method was also checked on Llama-3.1-8B-Instruct, where the diagnosis picked a different window.

Interesting ideas

  • I1. Before fixing a weak subset, compare paired cases where one condition succeeds and the other fails on the same item; this separates missing knowledge from failed access.
  • I2. Read out layer by layer where the correct signal builds up and where it disappears, then act only at that point instead of retraining everything.
  • I3. Use the model's own representation of an easy input as the alignment target for the hard input, so no external encoder or bridge is needed.
  • I4. Choose design parameters such as the layer window from diagnostic evidence, then report openly that other choices may win on particular metrics; this guards against tuning to the test set.
  • I5. Anchor an LLM judge on a reference reasoning field written by an expert, and check its outputs by hand, since such a judge favours factual accuracy and can miss short or code-switched answers.

For Mova

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

  • I1 (learn): Run parallel inputs, such as a sentence and its paraphrase, through the pipeline and count cases that pass one way but fail the other. This shows whether a broken stage lacks knowledge or simply fails to reach it.
  • I2 (tree): When probing gparse, trace layer by layer where correct head and label predictions emerge and then decay. Fine-tune or repair only that segment.
  • I3 (tree): When adapting gparse to a new UD dialect or noisy text, pull its hidden states toward the states of a clean, canonical parallel sentence.
  • I4 (learn): Pick repair-rule scopes or training subsets using diagnostics on a dev split, and keep the downstream test as a negative control.
  • I5 (answer): Score answers on fables or school tests against gold reasoning, and add a separate fluency check so terse answers are not over-rewarded.

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

🎓New York University Abu DhabiAbu Dhabi · United Arab Emirates49 works · 2,404 citations🏥Cleveland Clinic Abu DhabiAbu Dhabi · United Arab Emirates2 works · 5 citations

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 2Research subjects and languages the work is about.English · 1,373 worksSemitic languages · 1,484 works

Cite

Cite as Chaimae Abouzahir, Musa Khan, Hala Ali-Hassan, Congbo Ma, Khaled Saleh, Yousra Sadqi, Jihad Mallat, Walid Al-Eisawi, Nizar Habash and Farah E. Shamout. 2026. Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection. arXiv:2608.00207 · Findings of the Association for Computational Linguistics: EMNLP 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2608.00207 · arXiv 2608.00207

@misc{abouzahir2026bridging,
  title = {{Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection}},
  author = {Chaimae Abouzahir, Musa Khan, Hala Ali-Hassan, Congbo Ma, Khaled Saleh, Yousra Sadqi, Jihad Mallat, Walid Al-Eisawi, Nizar Habash and Farah E. Shamout},
  year = {2026},
  doi = {10.48550/arxiv.2608.00207},
  eprint = {2608.00207},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2608.00207}
}

References

70 references, 26 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Chaimae Abouzahir, Congbo Ma, Nizar Habash, and Farah E. Shamout. 2026. Cross-lingual empirical evaluation of large language models for Arabic medical tasks. In Proceedings of the 1st Workshop on Linguistic Analysis for Health (HeaLing 2026), pages 158–171, Rabat, Morocco. Association for Computational Linguistics. ↗
  2. Ashwag Alasmari, Sarah Alhumoud, and Waad Alshammari. 2024. AraMed: Arabic medical question answering using pretrained transformer language models. In Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024, pages 50–56, Torino, Italia. ELRA and ICCL.
  3. Iñigo Alonso, Maite Oronoz, and Rodrigo Agerri. 2024. Medexpqa: Multilingual benchmarking of large language models for medical question answering. Artificial Intelligence in Medicine, 155:102938. ↗
  4. Anthropic. 2026. Introducing Claude Opus 4.6. https://www.anthropic.com/news/ claude-opus-4-6. Accessed: 2026-05-03. ↗
  5. Mohamed Anwar, Abed Alhakim Freihat, George Ibrahim, Mostafa Awad, Abdelrahman Sadallah, Gurpreet Gosal, Gokulakrishnan Ramakrishnan, Sarath Chandran, Biswajit Mishra, Rituraj Joshi, and 1 others. 2026. Jais 2: A family of arabic-centric open large language models. arXiv preprint arXiv:2608.13580. ↗
  6. Rahul K. Arora, Jason Wei, Rebecca Soskin Hicks, Preston Bowman, Joaquin Quiñonero-Candela, Foivos Tsimpourlas, Michael Sharman, Meghan Shah, Andrea Vallone, Alex Beutel, Johannes Heidecke, and Karan Singhal. 2025. Healthbench: Evaluating large language models towards improved human health. Preprint, arXiv:2505.08775. ↗
  7. M Saiful Bari, Yazeed Alnumay, Norah A. Alzahrani, Nouf M. Alotaibi, Hisham Abdullah Alyahya, Sultan AlRashed, Faisal Abdulrahman Mirza, Shaykhah Z. Alsubaie, Hassan A. Alahmed, Ghadah Alabduljabbar, Raghad Alkhathran, Yousef Almushayqih, Raneem Alnajim, Salman Alsubaihi, Maryam Al Mansour, Saad Amin Hassan, Dr. Majed Alrubaian, Ali Alammari, Zaki Alawami, and 7 others. 2025. ALLam: Large language models for arabic and english. In The Thirteenth International Conference on Learning Representations.
  8. Shreya Bedi, Helen Cui, Michelle Fuentes, and 1 others. 2026. Holistic evaluation of large language models for medical tasks with Med-HELM. Nature Medicine, 32:943–951. find
  9. Nora Belrose, Igor Ostrovsky, Lev McKinney, Zach Furman, Logan Smith, Danny Halawi, Stella Biderman, and Jacob Steinhardt. 2023. Eliciting latent predictions from trans-Preprint, formers with the tuned lens. arXiv:2303.08112. ↗
  10. Basma El Amel Boussaha, Leen Al Qadi, Mugariya Farooq, Shaikha Alsuwaidi, Giulia Campesan, Ahmed Alzubaidi, Mohammed Alyafeai, and Hakim Hacid. 2025. 3LM: Bridging Arabic, STEM, and code through benchmarking. In Proceedings of The Third Arabic Natural Language Processing Conference, pages 42–63, Suzhou, China. Association for Computational Linguistics. ↗
  11. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, and 12 others. 2020. Language models are few-shot learners. Preprint, arXiv:2005.14165. ↗
  12. Zeming Chen, Alejandro Hernández Cano, Angelika Romanou, Antoine Bonnet, Kyle Matoba, Francesco Salvi, Matteo Pagliardini, Simin Fan, Andreas Köpf, Amirkeivan Mohtashami, Alexandre Sallinen, Alireza Sakhaeirad, Vinitra Swamy, Igor Krawczuk, Deniz Bayazit, Axel Marmet, Syrielle Montariol, Mary-Anne Hartley, Martin Jaggi, and Antoine Bosselut. 2023. Meditron-70b: Scaling medical pre-training for large language models. Preprint, arXiv:2311.16079. ↗
  13. Mouath Abu Daoud, Chaimae Abouzahir, Leen Kharouf, Walid Al-Eisawi, Nizar Habash, and Farah E. Shamout. 2025. Medarabiq: Benchmarking large language models on arabic medical tasks. In Proceedings of the 10th Machine Learning for Healthcare Conference, volume 298 of Proceedings of Machine Learning Research. PMLR. ↗
  14. Clément Christophe, Praveen K Kanithi, Tathagata Raha, Shadab Khan, and Marco AF Pimentel. 2024. Med42-v2: A suite of clinical llms. Preprint, arXiv:2408.06142. ↗
  15. Mouath Abu Daoud, Leen Kharouf, Omar El Hajj, Dana El Samad, Mariam Al-Omari, Jihad Mallat, Khaled Saleh, Nizar Habash, and Farah E. Shamout. 2026. Medarabench: Large-scale arabic medical question answering dataset and benchmark. In The Fourteenth International Conference on Learning Representations. ↗
  16. Alessio Cocchieri, Luca Ragazzi, Giuseppe Tagliavini, and Gianluca Moro. 2026. ReMedQA: Are we done with medical multiple-choice benchmarks? In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2706–2738, Rabat, Morocco. Association for Computational Linguistics. find
  17. DeepSeek-AI, Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenhao Xu, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, and 245 others. 2025. Deepseek-v3.2: Pushing the frontier of open large language models. Preprint, arXiv:2512.02556. ↗
  18. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, and 3416 others. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. Preprint, arXiv:2507.06261. ↗
  19. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 others. 2024. The llama 3 herd of models. Preprint, arXiv:2407.21783. ↗
  20. Yiming Cui, Ziqing Yang, and Xin Yao. 2024. Efficient and effective text encoding for chinese llama and alpaca. Preprint, arXiv:2304.08177. ↗
  21. John Dang, Shivalika Singh, Daniel D’souza, Arash Ahmadian, Alejandro Salamanca, Madeline Smith, Aidan Peppin, Sungjin Hong, Manoj Govindassamy, Terrence Zhao, Sandra Kublik, Meor Amer, Viraat Aryabumi, Jon Ander Campos, Yi-Chern Tan, Tom Kocmi, Florian Strub, Nathan Grinsztajn, Yannis Flet-Berliac, and 26 others. 2024. Aya expanse: Combining research breakthroughs for a new multilingual frontier. Preprint, arXiv:2412.04261. ↗
  22. Nizar Y. Habash. 2010. Introduction to Arabic Natural Language Processing, 1 edition. Synthesis Lectures on Human Language Technologies. Springer Cham. find
  23. Katharina Hämmerl, Jindřich Libovický, and Alexander Fraser. 2024. Understanding cross-lingual Alignment—A survey. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10922–10943, Bangkok, Thailand. Association for Computational Linguistics. find
  24. Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations.
  25. Peng Hu, Sizhe Liu, Changjiang Gao, Xin Huang, Xue Han, Junlan Feng, Chao Deng, and Shujian Huang. 2025. Large language models are cross-lingual knowledge-free reasoners. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1525–1542, Albuquerque, New Mexico. Association for Computational Linguistics. ↗
  26. Haoyang Huang, Tianyi Tang, Dongdong Zhang, Xin Zhao, Ting Song, Yan Xia, and Furu Wei. 2023. Not all languages are created equal in LLMs: Improving multilingual capability by cross-lingual-thought prompting. In The 2023 Conference on Empirical Methods in Natural Language Processing.
  27. Zixian Huang, Wenhao Zhu, Gong Cheng, Lei Li, and Fei Yuan. 2024. Mindmerger: Efficiently boosting LLM reasoning in non-english languages. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  28. Maxim Ifergan, Leshem Choshen, Roee Aharoni, Idan Szpektor, and Omri Abend. 2025. Beneath the surface of consistency: Exploring cross-lingual knowledge representation sharing in LLMs. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 4630–4644, Albuquerque, New Mexico. Association for Computational Linguistics. ↗
  29. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, and William El Sayed. 2023a. Mistral 7b. Preprint, arXiv:2310.06825. Lavender Yao Jiang, Xujin Chris Liu, Nima Pour Nejatian, Mustafa Nasir-Moin, Duo Wang, Anas Abidin, Kevin Eaton, Howard Antony Riina, Ilya Laufer, Paawan Punjabi, Madeline Miceli, Nora C. Kim, Cordelia Orillac, Zane Schnurman, Christopher Livia, Hannah Weiss, David Kurland, Sean Neifert, Yosef Dastagirzada, and 9 others. 2023b. Health system-scale language models are all-purpose prediction engines. Nature, 619:357–362. ↗
  30. Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William Cohen, and Xinghua Lu. 2019. Pub-MedQA: A dataset for biomedical research question answering. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2567–2577, Hong Kong, China. Association for Computational Linguistics. find
  31. Yiqiao Jin, Mohit Chandra, Gaurav Verma, Yibo Hu, Munmun De Choudhury, and Srijan Kumar. 2024. Better to ask in english: Cross-lingual evaluation of large language models for healthcare queries. In Proceedings of the ACM Web Conference 2024, WWW ’24, page 2627–2638, New York, NY, USA. Association for Computing Machinery. find
  32. Pratik Joshi, Sebastin Santy, Amar Budhiraja, Kalika Bali, and Monojit Choudhury. 2020. The state and fate of linguistic diversity and inclusion in the NLP world. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6282–6293, Online. Association for Computational Linguistics.
  33. Amir Hossein Kargaran, Ali Modarressi, Nafiseh Nikeghbal, Jana Diesner, François Yvon, and Hinrich Schuetze. 2025. MEXA: Multilingual evaluation of English-centric LLMs via cross-lingual alignment. In Findings of the Association for Computational Linguistics: ACL 2025, pages 27001–27023, Vienna, Austria. Association for Computational Linguistics. find
  34. Kazuma Kobayashi, Zhen Wan, Fei Cheng, Yuma Tsuta, Xin Zhao, Junfeng Jiang, Jiahao Huang, Zhiyi Huang, Yusuke Oda, Rio Yokota, Yuki Arase, Daisuke Kawahara, Akiko Aizawa, and Sadao Kurohashi. 2025. Leveraging high-resource English corpora for cross-lingual domain adaptation in low-resource Japanese medicine via continued pre-training. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 11469–11488, Suzhou, China. Association for Computational Linguistics. find
  35. Fajri Koto, Haonan Li, Sara Shatnawi, Jad Doughman, Abdelrahman Sadallah, Aisha Alraeesi, Khalid Almubarak, Zaid Alyafeai, Neha Sengupta, Shady Shehata, Nizar Habash, Preslav Nakov, and Timothy Baldwin. 2024. ArabicMMLU: Assessing massive multitask language understanding in Arabic. In Findings of the Association for Computational Linguistics: ACL 2024, pages 5622–5640, Bangkok, Thailand. Association for Computational Linguistics. ↗
  36. Danni Liu and Jan Niehues. 2025. Conditions for catastrophic forgetting in multilingual translation. In Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025), pages 347–359, Suzhuo, China. Association for Computational Linguistics. find
  37. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in GPT. In Advances in Neural Information Processing Systems, volume 35, pages 17359–17372. Curran Associates, Inc. ↗
  38. Mistral AI. 2025. Mistral-Small-3.2-24B-Instruct-2506. https://huggingface.co/mistralai/Mistral-Small-3. 2-24B-Instruct-2506. Hugging Face model card. Accessed: 2026-05-03. ↗
  39. Yazeed Al Moaiad, Mohammad Alobed, Mahmoud Alsakhnini, and Alaa M. Momani. 2024. Challenges in natural arabic language processing. Edelweiss Applied Science and Technology. ↗
  40. Zabir Al Nazi and Wei Peng. 2024. Large language models in healthcare and medical domain: A review. Preprint, arXiv:2401.06775. ↗
  41. Harsha Nori, Nicholas King, Scott Mayer McKinney, Dean Carignan, and Eric Horvitz. 2023. Capabilities of gpt-4 on medical challenge problems. Preprint, arXiv:2303.13375. ↗
  42. OpenAI. 2025. Introducing GPT-5.2. https://openai.com/index/ introducing-gpt-5-2/. Accessed: 2026-05-03. ↗
  43. Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2022. Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering. In Proceedings of the Conference on Health, Inference, and Learning, volume 174 of Proceedings of Machine Learning Research, pages 248–260. PMLR. ↗
  44. Sara Pieri, Sahal Shaji Mullappilly, Fahad Shahbaz Khan, Rao Muhammad Anwer, Salman Khan, Timothy Baldwin, and Hisham Cholakkal. 2024. BiMediX: Bilingual medical mixture of experts LLM. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16984–17002, Miami, Florida, USA. Association for Computational Linguistics. find
  45. Pengcheng Qiu, Chaoyi Wu, Xiaoman Zhang, and 1 others. 2024. Towards building multilingual language model for medicine. Nature Communications, 15:8384.
  46. Kartik Ravisankar, HyoJung Han, Sarah Wiegreffe, and Marine Carpuat. 2026. Can you map it to English? the role of cross-lingual alignment in the multilingual performance of LLMs. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4854–4872, Rabat, Morocco. Association for Computational Linguistics. find
  47. Nada Saadi, Tathagata Raha, Clement Christophe, Marco AF Pimentel, Ronnie Rajan, and Praveenkumar Kanithi. 2025. Bridging language barriers in healthcare: a study on arabic LLMs. In Workshop on Large Language Models and Generative AI for Health at AAAI 2025. ↗
  48. Alexandre Sallinen, Antoni-Joan Solergibert, Michael Zhang, Guillaume Boyé, Maud Dupont-Roc, Xavier Theimer-Lienhard, Etienne Boisson, Bastien Bernath, Hichem Hadhri, Antoine Tran, and 1 others. 2025. Llama-3-meditron: An open-weight suite of medical llms based on llama-3.1. In Workshop on Large Language Models and Generative AI for Health at AAAI 2025. find
  49. Lisa Schut, Yarin Gal, and Sebastian Farquhar. 2025. Do multilingual LLMs think in english? In ICLR 2025 Workshop on Building Trust in Language Models and Applications. Andrew Sellergren, Sahar Kazemzadeh, Tiam Jaroensri, Atilla Kiraly, Madeleine Traverse, Timo Kohlberger, Shawn Xu, Fayaz Jamil, Cían Hughes, Charles Lau, Justin Chen, Fereshteh Mahvar, Liron Yatziv, Tiffany Chen, Bram Sterling, Stefanie Anna Baby, Susanna Maria Baby, Jeremy Lai, Samuel Schmidgall, and 62 others. 2026. Medgemma technical report. Preprint, arXiv:2507.05201. ↗
  50. SILMA AI. 2026. SILMA-9B-Instruct-v1.0. https://huggingface.co/silma-ai/ SILMA-9B-Instruct-v1.0. Hugging Face model card. Accessed: 2026-05-03. ↗
  51. Karan Singhal, Shekoofeh Azizi, Tao Tu, S. Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, Perry Payne, Martin Seneviratne, Paul Gamble, Chris Kelly, Abubakr Babiker, Nathanael Schärli, Aakanksha Chowdhery, Philip Mansfield, Dina Demner-Fushman, and 13 others. 2023. Large language models encode clinical knowledge. Nature, 620(7972):172–180.
  52. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. Preprint, arXiv:2302.13971. ↗
  53. Tao Tu, Mike Schaekermann, Anil Palepu, and 1 others. 2025. Towards conversational diagnostic artificial intelligence. Nature, 642:442–450. find
  54. Tu Vu, Aditya Barua, Brian Lester, Daniel Cer, Mohit Iyyer, and Noah Constant. 2022. Overcoming catastrophic forgetting in zero-shot cross-lingual generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9279–9300, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  55. Karan Singhal, Tao Tu, Juraj Gottweis, and 1 others. 2025. Toward expert-level medical question answering with large language models. Nature Medicine, 31:943–950. find
  56. Haochun Wang, Chi Liu, Nuwa Xi, Zewen Qiang, Sendong Zhao, Bing Qin, and Ting Liu. 2023a. Huatuo: Tuning llama model with chinese medical knowledge. Preprint, arXiv:2304.06975. ↗
  57. Statista. 2023. The most spoken languages worldwide in 2023. https://www.statista.com/statistics/266808/ the-most-spoken-languages-worldwide/. Accessed: 2026-04-20. ↗
  58. Xidong Wang, Nuo Chen, Junyin Chen, Yidong Wang, Guorui Zhen, Chunxian Zhang, Xiangbo Wu, Yan Hu, Anningzhe Gao, Xiang Wan, Haizhou Li, and Benyou Wang. 2024. Apollo: A lightweight multilingual medical llm towards democratizing medical ai to 6b people. Preprint, arXiv:2403.03640. ↗
  59. Fanar Team, Ummar Abbas, Mohammad Shahmeer Ahmad, Firoj Alam, Enes Altinisik, Ehsannedin Asgari, Yazan Boshmaf, Sabri Boughorbel, Sanjay Chawla, Shammur Chowdhury, Fahim Dalvi, Kareem Darwish, Nadir Durrani, Mohamed Elfeky, Ahmed Elmagarmid, Mohamed Eltabakh, Masoomali Fatehkia, Anastasios Fragkopoulos, Maram Hasanain, and 23 others. 2025a. Fanar: An arabic-centric multimodal generative ai platform. Preprint, arXiv:2501.13944. ↗
  60. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penchev, and 197 others. 2025b. Gemma 3 technical report. Preprint, arXiv:2503.19786. ↗
  61. Yuqing Wang, Yun Zhao, and Linda Petzold. 2023b. Are large language models ready for healthcare? a comparative study on clinical language understanding. In Proceedings of the 8th Machine Learning for Healthcare Conference, volume 219 of Proceedings of Machine Learning Research, pages 804–823. PMLR. ↗
  62. Chris Wendler, Veniamin Veselovsky, Giovanni Monea, and Robert West. 2024. Do llamas work in English? on the latent language of multilingual transformers. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15366–15394, Bangkok, Thailand. Association for Computational Linguistics.
  63. BigScience Workshop. 2024. Bloom: A 176bparameter open-access multilingual language model. Journal of Machine Learning Research, 25(422):1–74. find
  64. Dongkeun Yoon, Joel Jang, Sungdong Kim, Seungone Kim, Sheikh Shafayat, and Minjoon Seo. 2024. LangBridge: Multilingual reasoning without multilingual supervision. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7502–7522, Bangkok, Thailand. Association for Computational Linguistics. ↗
  65. Yongheng Zhang, Qiguang Chen, Min Li, Wanxiang Che, and Libo Qin. 2024. AutoCAP: Towards automatic cross-lingual alignment planning for zero-shot chain-of-thought. In Findings of the Association for Computational Linguistics: ACL 2024, pages 9191–9200, Bangkok, Thailand. Association for Computational Linguistics. find
  66. Weixiang Zhao, Yulin Hu, Jiahe Guo, Xingyu Sui, Tongtong Wu, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che, and Ting Liu. 2025. Lens: Rethinking multilingual enhancement for large language models. ↗
  67. Xin Zhao, Naoki Yoshinaga, Yuma Tsuta, and Akiko Aizawa. 2026. Tracing multilingual knowledge acquisition dynamics in domain adaptation: A case study of biomedical adaptation. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5739–5760, Rabat, Morocco. Association for Computational Linguistics. find
  68. Guorui Zheng, Xidong Wang, Juhao Liang, Nuo Chen, Yuping Zheng, and Benyou Wang. 2025. Efficiently democratizing medical LLMs for 50 languages via a mixture of language family experts. In The Thirteenth International Conference on Learning Representations. ↗
  69. Yuxuan Zhou, Xien Liu, Xiao Zhang, Chen Ning, Shijin Wang, Guoping Hu, and Ji Wu. 2026. Investigating and mitigating catastrophic forgetting in medical knowledge injection through internal knowledge augmentation learning. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. find
  70. Jingwei Zuo, Maksim Velikanov, Ilyas Chahed, Younes Belkada, Dhia Eddine Rhayem, Guillaume Kunsch, Hakim Hacid, Hamza Yous, Brahim Farhat, Ibrahim Khadraoui, Mugariya Farooq, Giulia Campesan, Ruxandra Cojocaru, Yasser Djilali, Shi Hu, Iheb Chaabane, Puneesh Khanna, Mohamed El Amine Seddik, Ngoc Dung Huynh, and 8 others. 2025. Falcon-h1: A family of hybrid-head language models redefining efficiency and performance. Preprint, arXiv:2507.22448. ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/abouzahir-2026-bridging-english-arabic-medical-knowledge/