# PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation

arXiv: https://arxiv.org/abs/2205.12206 · HTML: https://mlsanity.com/paper/2205.12206/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 42 references that are in the map.
- First posted on arXiv 24 May 2022.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Domain Control for Neural Machine Translation](https://mlsanity.com/paper/1612.06140/) (2016)
- [Controlling the Output Length of Neural Machine Translation](https://mlsanity.com/paper/1910.10408/) (2019)
- [Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhyme](https://mlsanity.com/paper/1807.03491/) (2018)
- [DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling](https://mlsanity.com/paper/2107.01875/) (2021)
- [Chinese Poetry Generation with Planning based Neural Network](https://mlsanity.com/paper/1610.09889/) (2016)
- [Does Corpus Quality Really Matter for Low-Resource Languages?](https://mlsanity.com/paper/2203.08111/) (2022)
- [Flexible and Creative Chinese Poetry Generation Using Neural Memory](https://mlsanity.com/paper/1705.03773/) (2017)
- [Learning Rhyming Constraints using Structured Adversaries](https://mlsanity.com/paper/1909.06743/) (2019)
- [A Multi-Modal Chinese Poetry Generation Model](https://mlsanity.com/paper/1806.09792/) (2018)
- [DISCO PAL: Diachronic Spanish Sonnet Corpus with Psychological and Affective Labels](https://mlsanity.com/paper/2007.04626/) (2020)

## Built on by (most cited first, 22 of 22)

- [Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing](https://mlsanity.com/paper/2210.13669/) (2022)
- [ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models](https://mlsanity.com/paper/2212.10474/) (2022)
- [Sonnet or Not, Bot? Poetry Evaluation for Large Models and Datasets](https://mlsanity.com/paper/2406.18906/) (2024)
- [Does ChatGPT Have a Poetic Style?](https://mlsanity.com/paper/2410.15299/) (2024)
- [Songs Across Borders: Singable and Controllable Neural Lyric Translation](https://mlsanity.com/paper/2305.16816/) (2023)
- [Towards Enhanced Immersion and Agency for LLM-based Interactive Drama](https://mlsanity.com/paper/2502.17878/) (2025)
- [Can AI Write Classical Chinese Poetry like Humans? An Empirical Study Inspired by Turing Test](https://mlsanity.com/paper/2401.04952/) (2024)
- [PhonologyBench: Evaluating Phonological Skills of Large Language Models](https://mlsanity.com/paper/2404.02456/) (2024)
- [Creativity in AI: Progresses and Challenges](https://mlsanity.com/paper/2410.17218/) (2024)
- [What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering](https://mlsanity.com/paper/2601.20164/) (2026)
- [Creative Data Generation: A Review Focusing on Text and Poetry](https://mlsanity.com/paper/2305.08493/) (2023)
- [ALBERTI, a Multilingual Domain Specific Language Model for Poetry Analysis](https://mlsanity.com/paper/2307.01387/) (2023)
- [Conditioning LLMs to Generate Code-Switched Text](https://mlsanity.com/paper/2502.12924/) (2025)
- [POEMetric: The Last Stanza of Humanity](https://mlsanity.com/paper/2604.03695/) (2026)
- [Joint Learning of Wording and Formatting for Singable Melody-to-Lyric Generation](https://mlsanity.com/paper/2307.02146/) (2023)
- [MetricalARGS: A Taxonomy for Studying Metrical Poetry with LLMs](https://mlsanity.com/paper/2510.08188/) (2025)
- [Instruction-Guided Poetry Generation in Arabic and Its Dialects](https://mlsanity.com/paper/2604.27766/) (2026)
- [Encoder-Decoder Framework for Interactive Free Verses with Generation with Controllable High-Quality Rhyming](https://mlsanity.com/paper/2405.05176/) (2024)
- [PROPOE 2: Avanccos na S'intese Computacional de Poemas Baseados em Prosa Liter'aria Brasileira](https://mlsanity.com/paper/2412.15263/) (2024)
- [Creating a digital poet](https://mlsanity.com/paper/2602.16578/) (2026)
- [Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese](https://mlsanity.com/paper/2606.07300/) (2026)
- [Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features](https://mlsanity.com/paper/2608.28986/) (2026)

## Abstract (arXiv)

Formal verse poetry imposes strict constraints on the meter and rhyme scheme of poems. Most prior work on generating this type of poetry uses existing poems for supervision, which are difficult to obtain for most languages and poetic forms. In this work, we propose an unsupervised approach to generate poems following any given meter and rhyme scheme, without requiring any poetic text for training. Our method works by splitting a regular, non-poetic corpus into phrases, prepending control codes that describe the length and end rhyme of each phrase, and training a transformer language model in the augmented corpus. During inference, we build control codes for the desired meter and rhyme scheme, and condition our language model on them to generate formal verse poetry. Experiments in Spanish and Basque show that our approach is able to generate valid poems, which are often comparable in quality to those written by humans.