---
title: "Instruction-Guided Poetry Generation in Arabic and Its Dialects"
description: "Research on Arabic poetry with LLMs has mostly covered analysis, such as meter detection or poet… 40 references, cited by 2 papers here."
authors: ["Abdelrahman Sadallah", "Kareem Elozeiri", "Mervat Abassy", "Rania Elbadry", "Mohamed Anwar", "Abed Alhakim Freihat", "Preslav Nakov", "Fajri Koto"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1931/"
doi: "10.18653/v1/2026.findings-acl.1931"
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/sadallah-2026-instruction-guided-poetry-generation-arabic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sadallah-2026-instruction-guided-poetry-generation-arabic/)

[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/7/) / Instruction-Guided Poetry Generation in Arabic and Its Dialects

# Instruction-Guided Poetry Generation in Arabic and Its Dialects

**Authors:** [Abdelrahman Sadallah](https://md.research.elamur.ai/free/en/authors/abdelrahman-sadallah/), [Kareem Elozeiri](https://md.research.elamur.ai/free/en/authors/kareem-elozeiri/), [Mervat Abassy](https://md.research.elamur.ai/free/en/authors/mervat-abassy/), [Rania Elbadry](https://md.research.elamur.ai/free/en/authors/rania-elbadry/), [Mohamed Anwar](https://md.research.elamur.ai/free/en/authors/mohamed-anwar/), [Abed Alhakim Freihat](https://md.research.elamur.ai/free/en/authors/abed-alhakim-freihat/), [Preslav Nakov](https://md.research.elamur.ai/free/en/authors/preslav-nakov/) and [Fajri Koto](https://md.research.elamur.ai/free/en/authors/fajri-koto/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/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.findings-acl.1931/) · [PDF](https://aclanthology.org/2026.findings-acl.1931.pdf) · [DOI 10.18653/v1/2026.findings-acl.1931](https://doi.org/10.18653/v1/2026.findings-acl.1931) · [OpenAlex](https://openalex.org/W7166875545)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/sadallah-2026-instruction-guided-poetry-generation-arabic/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Research on Arabic poetry with LLMs has mostly covered analysis, such as meter detection or poet attribution. Controllable generation, where a user sets constraints like meter, rhyme, era or dialect, has received little attention. The authors treat Arabic poetry writing as an instruction-following problem.

They gathered poems from several public websites, including Adab, Al-Diwan and PoetsGate. They merged these into one cleaned corpus with harmonized metadata, added keywords and keyphrases, and removed duplicates. From this corpus they built an instruction fine-tuning dataset with four tasks: generation, continuation, revision and multiple-choice analysis. The instruction templates were written by hand in MSA and four dialect groups.

Four LLMs were adapted with LoRA, comparing randomly mixed training against a curriculum ordered by difficulty. Automatic metrics, an LLM judge and native-speaker raters all show that fine-tuning improves constraint adherence and output quality, with ALLaM-7B performing best. Poetic creativity still leaves clear room for improvement. The released resource gives Arabic NLP a basis for user-guided creative writing tools that work across dialects.

## Key points
- **Dataset scale:** 4 core tasks split into 54 subtasks and 3,220 manually written templates. The templates cover MSA plus the Gulf, Levantine, North African and Nile Valley dialects, yielding about 1.35M training and 24.8K test pairs.
- **Models and training:** Fanar, Allam, Qwen3 and LLaMA-3.1 were fine-tuned with LoRA under joint (random mix) and curriculum regimes.
- **Data cleaning:** single-verse poems were dropped. Missing rhyme labels were inferred when at least 70% of verse endings matched.
- **Main results:** ALLaM-7B came out strongest. ANOVA showed the differences between models were significant (p \< 0.0001). The human-rated poetic quality score of 3.82/5 points to remaining limits in creativity.
- **Evaluation and limitations:** the LLM judge scored outputs consistently lower than human raters did. The source poetry is mostly historical MSA, so native dialectal and contemporary verse are underrepresented. Data and code are released at github.com/mbzuai-nlp/instructpoet-ar.

*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

- [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, United Arab Emirates · 124 works · 5,676 citations

📚 Shelves (4): [🖥️ 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

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

## Cite

Cite as: Abdelrahman Sadallah, Kareem Elozeiri, Mervat Abassy, Rania Elbadry, Mohamed Anwar, Abed Alhakim Freihat, Preslav Nakov and Fajri Koto. 2026. Instruction-Guided Poetry Generation in Arabic and Its Dialects. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{sadallah2026instruction,
  title = {{Instruction-Guided Poetry Generation in Arabic and Its Dialects}},
  author = {Abdelrahman Sadallah, Kareem Elozeiri, Mervat Abassy, Rania Elbadry, Mohamed Anwar, Abed Alhakim Freihat, Preslav Nakov and Fajri Koto},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1931},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1931}
}
```

- [← previous Instant Personalized Large Language Model Adaptation via Hypernetwork](https://md.research.elamur.ai/free/en/papers/tan-2026-instant-personalized-large-language-model/)
- [next → IREASONER: Trajectory-Aware Intrinsic Reasoning Supervision for Self-Evolving Large Multimodal Models](https://md.research.elamur.ai/free/en/papers/sunil-2026-ireasoner-trajectory-aware-intrinsic-reasoning/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/7/)

## References

40 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mourad Abbas, Mohamed Lichouri, and Ahmed Zeg-gada. 2019. Classification of arabic poems: from the 5th to the 15th century. In New Trends in Image Analysis and Processing – ICIAP 2019: ICIAP International Workshops, BioFor, PatReCH, e-BADLE, DeepRetail, and Industrial Session, Trento, Italy, September 9–10, 2019, Revised Selected Papers, page 179–186, Berlin, Heidelberg. Springer-Verlag. [find](https://scholar.google.com/scholar?q=Mourad+Abbas%2C+Mohamed+Lichouri%2C+and+Ahmed+Zeg%2Dgada%2E+2019%2E+Classification+of+arabic+poems%3A+from+the+5th+to+the+15th+century%2E+In+New+Trends+in+Image+Analysis+and+Processing+%E2%80%93+ICIAP+2019%3A+ICIAP+Internati)
2. Ummar Abbas, Mohammad Shahmeer Ahmad, Firoj Alam, Enes Altinisik, Ehsaneddin Asgari, Yazan Boshmaf, Sabri Boughorbel, Sanjay Chawla, Shammur A. Chowdhury, Fahim Dalvi, Kareem Darwish, Nadir Durrani, Mohamed Elfeky, Ahmed K. Elmagarmid, Mohamed Y. Eltabakh, Masoomali Fatehkia, Anastasios Fragkopoulos, Maram Hasanain, Majd Hawasly, and 22 others. 2025. [Fanar: An Arabic-centric multimodal generative AI platform](https://md.research.elamur.ai/free/en/papers/abbas-2025-fanar-arabic-centric-multimodal-generative/). ArXiv preprint, abs/2501.13944. [↗](https://arxiv.org/abs/2501.13944)
3. Munef Abdullah Ahmed, Raed Abdulkareem Hasan, Mostafa Abdulghafoor Mohammed, Peter Mwangi, and Tirus Muya. 2025. Classification arabic language (classical Arabic poetry, al-hur Arabic poetry and prose) using machine learning. EDRAAK, pages 94–104. [↗](https://doi.org/10.70470/edraak/2025/012)
4. Wafa Al Ghallabi, Ritesh Thawkar, Sara Ghaboura, Ketan Pravin More, Omkar Thawakar, Hisham Cholakkal, Salman Khan, and Rao Muhammad Anwer. 2025. [Fann or flop: A multigenre, multiera benchmark for Arabic poetry understanding in LLMs](https://md.research.elamur.ai/free/en/papers/ghallabi-2025-fann-or-flop-multigenre-multiera/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 20224–20244, Suzhou, China. Association for Computational Linguistics.
5. Muhsin J Al-Musawi. 2006. Arabic poetry: Trajectories of modernity and tradition. Routledge, London, UK. [find](https://scholar.google.com/scholar?q=Muhsin+J+Al%2DMusawi%2E+2006%2E+Arabic+poetry%3A+Trajectories+of+modernity+and+tradition%2E+Routledge%2C+London%2C+UK%2E)
6. Badriyya B. Al-Onazi, Wadee A. Nashir, and Asma A. Al-Shargabi. 2025. Diwan: constructing the largest annotated corpus for arabic poetry. IEEE Access, 13:58927–58941. [↗](https://doi.org/10.1109/access.2025.3551161)
7. Maged Saeed AlShaibani, Zaid Alyafeai, and Irfan Ahmad. 2020. Meter classification of arabic poems using deep bidirectional recurrent neural networks. Pattern Recognit. Lett., 136:1–7. [find](https://scholar.google.com/scholar?q=Maged+Saeed+AlShaibani%2C+Zaid+Alyafeai%2C+and+Irfan+Ahmad%2E+2020%2E+Meter+classification+of+arabic+poems+using+deep+bidirectional+recurrent+neural+networks%2E+Pattern+Recognit%2E+Lett%2E%2C+136%3A1%E2%80%937%2E)
8. Zaid Alyafeai, Maged Saeed AlShaibani, and Moataz Ahmad. 2023. [Ashaar: Automatic analysis and generation of arabic poetry using deep learning approaches](https://md.research.elamur.ai/free/en/papers/alyafeai-2023-ashaar-automatic-analysis-generation-arabic/). ArXiv preprint, abs/2307.06218. [↗](https://arxiv.org/abs/2307.06218)
9. Ron Artstein and Massimo Poesio. 2008. [Inter-coder agreement for computational linguistics](https://md.research.elamur.ai/free/en/papers/artstein-2008-survey-article-inter-coder-agreement/). Computational Linguistics, 34(4):555–596. [↗](https://doi.org/10.1162/coli.07-034-r2)
10. Muhammad Mustafa Badawi. 1975. A critical introduction to modern Arabic poetry. Cambridge University Press, Cambridge, UK. [↗](https://doi.org/10.1017/cbo9780511554124)
11. 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, Majed Alrubaian, Ali Alammari, Zaki Alawami, and 2 others. 2025. [ALLaM: Large Language Models for Arabic and English](https://md.research.elamur.ai/free/en/papers/bari-2024-allam-large-language-models-arabic/). In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025.
12. Jonas Belouadi and Steffen Eger. 2023. ByGPT5: End-to-end style-conditioned poetry generation with token-free language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7364–7381, Toronto, Canada. Association for Computational Linguistics. [↗](https://doi.org/10.48448/fd88-jg30)
13. Tuhin Chakrabarty, Vishakh Padmakumar, and He He. 2022. Help me write a poem: Instruction tuning as a vehicle for collaborative poetry writing. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6848–6863, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Tuhin+Chakrabarty%2C+Vishakh+Padmakumar%2C+and+He+He%2E+2022%2E+Help+me+write+a+poem%3A+Instruction+tuning+as+a+vehicle+for+collaborative+poetry+writing%2E+In+Proceedings+of+the+2022+Conference+on+Empirical+Metho)
14. Tuhin Chakrabarty, Vishakh Padmakumar, He He, and Nanyun Peng. 2023. Creative natural language generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, pages 34–40, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Tuhin+Chakrabarty%2C+Vishakh+Padmakumar%2C+He+He%2C+and+Nanyun+Peng%2E+2023%2E+Creative+natural+language+generation%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Natural+Language+Processing%3A+Tu)
15. Jacob Cohen. 1968. Weighted kappa: nominal scale agreement with provision for scaled disagreement or partial credit. Psychological Bulletin, 70(4):213–220. [find](https://scholar.google.com/scholar?q=Jacob+Cohen%2E+1968%2E+Weighted+kappa%3A+nominal+scale+agreement+with+provision+for+scaled+disagreement+or+partial+credit%2E+Psychological+Bulletin%2C+70%284%29%3A213%E2%80%93220%2E)
16. Nehal Elkaref, Mervat Abu-Elkheir, Maryam ElOraby, and Mohamed Abdelgaber. 2022. [Generating classical Arabic poetry using pre-trained models](https://md.research.elamur.ai/free/en/papers/eloraby-2022-generating-classical-arabic-poetry-pre/). In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 53–62, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics. [↗](https://doi.org/10.60692/k341d-hs929)
17. Mohamad Elzohbi and Richard Zhao. 2025. [Tahḏīb: A rhythm-aware phrase insertion for classical Arabic poetry composition](https://md.research.elamur.ai/free/en/papers/elzohbi-2025-tah-ib-rhythm-aware-phrase/). In Proceedings of The Third Arabic Natural Language Processing Conference, pages 194–202, Suzhou, China. Association for Computational Linguistics. [↗](https://doi.org/10.48448/6gck-yf20)
18. Leo Gao, Jonathan Tow, Baber Abbasi, Stella Biderman, Sid Black, Anthony DiPofi, Charles Foster, Laurence Golding, Jeffrey Hsu, Alain Le Noac’h, Haonan Li, Kyle McDonell, Niklas Muennighoff, Chris Ociepa, Jason Phang, Laria Reynolds, Hailey Schoelkopf, Aviya Skowron, Lintang Sutawika, and 5 others. 2023. A framework for few-shot language model evaluation. [find](https://scholar.google.com/scholar?q=Leo+Gao%2C+Jonathan+Tow%2C+Baber+Abbasi%2C+Stella+Biderman%2C+Sid+Black%2C+Anthony+DiPofi%2C+Charles+Foster%2C+Laurence+Golding%2C+Jeffrey+Hsu%2C+Alain+Le+Noac%E2%80%99h%2C+Haonan+Li%2C+Kyle+McDonell%2C+Niklas+Muennighoff%2C+Chris+Oci)
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](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/).
20. Hani D. Hejazi, Ahmed A. Khamees, Muhammad Turki Alshurideh, and Said A. Salloum. 2021. Arabic text generation: Deep learning for poetry synthesis. In Advances in Machine Learning and Data Analytics. Springer. [find](https://scholar.google.com/scholar?q=Hani+D%2E+Hejazi%2C+Ahmed+A%2E+Khamees%2C+Muhammad+Turki+Alshurideh%2C+and+Said+A%2E+Salloum%2E+2021%2E+Arabic+text+generation%3A+Deep+learning+for+poetry+synthesis%2E+In+Advances+in+Machine+Learning+and+Data+Analytics%2E+)
21. Hisar Maruli Manurung. 2004. An Evolutionary Algorithm Approach to Poetry Generation. Ph.D. thesis, University of Edinburgh. [find](https://scholar.google.com/scholar?q=Hisar+Maruli+Manurung%2E+2004%2E+An+Evolutionary+Algorithm+Approach+to+Poetry+Generation%2E+Ph%2ED%2E+thesis%2C+University+of+Edinburgh%2E)
22. A. M. Mutawa and Ayshah Alrumaih. 2025. Determining the meter of classical arabic poetry using deep learning: a performance analysis. Frontiers in Artificial Intelligence, 8. [↗](https://doi.org/10.3389/frai.2025.1523336)
23. Mariam Orabi, Hozayfa El Rifai, and Ashraf Elnagar. 2020. Classical Arabic poetry: classification based on era. In 2020 IEEE/ACS 17th International Conference on Computer Systems and Applications (AICCSA), pages 1–6, Antalya, Turkey. [↗](https://doi.org/10.17632/mcj6vkg6zw)
24. Aitor Ormazabal, Mikel Artetxe, Manex Agirrezabal, Aitor Soroa, and Eneko Agirre. 2022. PoeLM: A meter- and rhyme-controllable language model for unsupervised poetry generation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3655–3670, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Aitor+Ormazabal%2C+Mikel+Artetxe%2C+Manex+Agirrezabal%2C+Aitor+Soroa%2C+and+Eneko+Agirre%2E+2022%2E+PoeLM%3A+A+meter%2D+and+rhyme%2Dcontrollable+language+model+for+unsupervised+poetry+generation%2E+In+Findings+of+the+Ass)
25. Faisal Qarah. 2024. [AraPoemBERT: a pretrained language model for arabic poetry analysis](https://md.research.elamur.ai/free/en/papers/qarah-2024-arapoembert-pretrained-language-model-arabic/). arXiv preprint arXiv:2403.12392. [↗](https://arxiv.org/abs/2403.12392)
26. Sakib Shahriar, Noora Al Roken, and Imran Zualkernan. 2023. Classification of arabic poetry emotions using deep learning. Computers, 12(5). [↗](https://doi.org/10.3390/computers12050089)
27. Sameerah Talafha and Banafsheh Rekabdar. 2021. Poetry generation model via deep learning incorporating extended phonetic and semantic embeddings. In 2021 IEEE 15th International Conference on Semantic Computing (ICSC), pages 48–55, Laguna Hills, CA, USA. [find](https://scholar.google.com/scholar?q=Sameerah+Talafha+and+Banafsheh+Rekabdar%2E+2021%2E+Poetry+generation+model+via+deep+learning+incorporating+extended+phonetic+and+semantic+embeddings%2E+In+2021+IEEE+15th+International+Conference+on+Semantic)
28. Zhe Wang, Wei He, Hua Wu, Haiyang Wu, Wei Li, Haifeng Wang, and Enhong Chen. 2016. Chinese poetry generation with planning based neural network. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1051–1060, Osaka, Japan. [↗](https://doi.org/10.48550/arxiv.1610.09889)
29. The COLING 2016 Organizing Committee. [find](https://scholar.google.com/scholar?q=The+COLING+2016+Organizing+Committee%2E)
30. Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, and Colin Raffel. 2022. ByT5: Towards a token-free future with pre-trained byte-to-byte models. Transactions of the Association for Computational Linguistics, 10:291–306. [↗](https://doi.org/10.1162/tacl_a_00461)
31. 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](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net.
32. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/).
33. Salma Jayyusi. 1977. Trends and Movements in Modern Arabic Poetry. Brill, Leiden, The Netherlands. [↗](https://doi.org/10.1163/9789004663008)
34. Xiaoyuan Yi, Maosong Sun, Ruoyu Li, and Wenhao Li. 2018. Automatic poetry generation with mutual reinforcement learning. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3143–3153, Brussels, Belgium. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Xiaoyuan+Yi%2C+Maosong+Sun%2C+Ruoyu+Li%2C+and+Wenhao+Li%2E+2018%2E+Automatic+poetry+generation+with+mutual+reinforcement+learning%2E+In+Proceedings+of+the+2018+Conference+on+Empirical+Methods+in+Natural+Language+)
35. J. Richard Landis and Gary G. Koch. 1977. The measurement of observer agreement for categorical data. Biometrics, 33(1):159–174. [↗](https://doi.org/10.2307/2529310)
36. Chengyue Yu, Lei Zang, Jiaotuan Wang, Chenyi Zhuang, and Jinjie Gu. 2024. CharPoet: A Chinese classical poetry generation system based on token-free LLM. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 315–325, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Chengyue+Yu%2C+Lei+Zang%2C+Jiaotuan+Wang%2C+Chenyi+Zhuang%2C+and+Jinjie+Gu%2E+2024%2E+CharPoet%3A+A+Chinese+classical+poetry+generation+system+based+on+token%2Dfree+LLM%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+t)
37. Ran Zhang and Steffen Eger. 2024. LLM-based multi-agent poetry generation in non-cooperative environments. arXiv preprint arXiv:2409.03659. [↗](https://arxiv.org/abs/2409.03659)
38. Xingxing Zhang and Mirella Lapata. 2014. [Chinese poetry generation with recurrent neural networks](https://md.research.elamur.ai/free/en/papers/zhang-2014-chinese-poetry-generation-recurrent-neural/). In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 670–680, Doha, Qatar. Association for Computational Linguistics.
39. Lianghui Zhu, Xinggang Wang, and Xinlong Wang. 2025. [Judgelm: Fine-tuned large language models are scalable judges](https://md.research.elamur.ai/free/en/papers/zhu-2023-judgelm-fine-tuned-large-language/). In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net.
40. Michael Zwettler. 1978. The oral tradition of classical Arabic poetry: its character and implications. Ohio State University Press, Columbus. [find](https://scholar.google.com/scholar?q=Michael+Zwettler%2E+1978%2E+The+oral+tradition+of+classical+Arabic+poetry%3A+its+character+and+implications%2E+Ohio+State+University+Press%2C+Columbus%2E)

*Updated 1 November 2026*