# Acrostic Poem Generation

arXiv: https://arxiv.org/abs/2010.02239 · HTML: https://mlsanity.com/paper/2010.02239/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 10 of 10)

- [Evaluating Diversity in Automatic Poetry Generation](https://mlsanity.com/paper/2406.15267/) (2024)
- [TwistList: Resources and Baselines for Tongue Twister Generation](https://mlsanity.com/paper/2306.03457/) (2023)
- [Does ChatGPT Have a Poetic Style?](https://mlsanity.com/paper/2410.15299/) (2024)
- [ReFF: Reinforcing Format Faithfulness in Language Models across Varied Tasks](https://mlsanity.com/paper/2412.09173/) (2024)
- [Creativity in AI: Progresses and Challenges](https://mlsanity.com/paper/2410.17218/) (2024)
- [Aesthetics of Sanskrit Poetry from the Perspective of Computational Linguistics: A Case Study Analysis on Siksastaka](https://mlsanity.com/paper/2308.07081/) (2023)
- [PoemTale Diffusion: Minimising Information Loss in Poem to Image Generation with Multi-Stage Prompt Refinement](https://mlsanity.com/paper/2507.13708/) (2025)
- [AcrosticSleuth: Probabilistic Identification and Ranking of Acrostics in Multilingual Corpora](https://mlsanity.com/paper/2408.04427/) (2024)
- [Detecting Spelling and Grammatical Anomalies in Russian Poetry Texts](https://mlsanity.com/paper/2505.04507/) (2025)
- [Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features](https://mlsanity.com/paper/2608.28986/) (2026)

## Abstract (arXiv)

We propose a new task in the area of computational creativity: acrostic poem generation in English. Acrostic poems are poems that contain a hidden message; typically, the first letter of each line spells out a word or short phrase. We define the task as a generation task with multiple constraints: given an input word, 1) the initial letters of each line should spell out the provided word, 2) the poem's semantics should also relate to it, and 3) the poem should conform to a rhyming scheme. We further provide a baseline model for the task, which consists of a conditional neural language model in combination with a neural rhyming model. Since no dedicated datasets for acrostic poem generation exist, we create training data for our task by first training a separate topic prediction model on a small set of topic-annotated poems and then predicting topics for additional poems. Our experiments show that the acrostic poems generated by our baseline are received well by humans and do not lose much quality due to the additional constraints. Last, we confirm that poems generated by our model are indeed closely related to the provided prompts, and that pretraining on Wikipedia can boost performance.