arXiv：cs.CL· Ahmad Abbas, Tamara Fakih, Nour Fakih, Ammar Mohanna·· 3 小时前AI 评分35
Shaer：可控古典阿拉伯语诗歌生成，联合韵律子形式与语义条件
Shaer: Controlled Arabic Poetry Generation with Meter Subform and Semantic Conditioning
AI 导读
Shaer 是一个可控古典阿拉伯语诗歌生成框架，联合以自然语言描述、韵律子形式和目标半句数为条件。研究构建了包含 116,032 首古典阿拉伯语诗歌的语料库，并用 QLoRA 监督微调 Yehia-7B。
正文
Abstract:Classical Arabic poetry generation requires simultaneously satisfying semantic, linguistic, and fine-grained prosodic constraints. Existing systems typically control broad poetic attributes but do not jointly model semantic intent, meter subform, and poem length. We present Shaer, a controllable Classical Arabic poetry generation framework jointly conditioned on natural-language descriptions, meter subforms, and target hemistich counts. To support this task, we construct an enriched corpus of 116,032 classical Arabic poems derived from Ashaar, containing normalized meter-subform labels and automatically generated, validated semantic descriptions. We then adapt Yehia-7B using QLoRA-based supervised fine-tuning with a completion-only objective. Our evaluation combines automatic assessment of base-meter conformity, requested-subform adherence, and length control with three LLM judges, blinded human evaluation, and memorization analysis. Shaer achieves 95.17% base-meter accuracy, 91.75% poem-level meter-subform accuracy, and 83.40% exact count accuracy. Relative to its untuned foundation model, these results represent gains of 68.68, 57.77, and 38.93 percentage points, respectively; Shaer also attains the highest base-meter accuracy among all evaluated systems. Multi-LLM evaluation and a blinded human assessment of top-ranked outputs further indicate competitive semantic and literary quality. Finally, analysis of all 3,481 test generations finds no exact copies from the training corpus or paired source poems. Code, models, and datasets are publicly available.
| Comments: | 22 pages, 7 figures. Code: this https URL ; models and datasets: this https URL |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.09756 [cs.CL] |
| (or arXiv:2610.09756v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09756 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ahmad Abbas [view email]
[v1]
Wed, 7 Oct 2026 09:44:21 UTC (4,105 KB)
来源：arXiv：cs.CL · arxiv.org