# CharPoet: A Chinese Classical Poetry Generation System Based on Token-free LLM

arXiv: https://arxiv.org/abs/2401.03512 · HTML: https://mlsanity.com/paper/2401.03512/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 7 Jan 2024.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [What do tokens know about their characters and how do they know it?](https://mlsanity.com/paper/2206.02608/) (2022)
- [Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens](https://mlsanity.com/paper/2108.11193/) (2021)
- [ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models](https://mlsanity.com/paper/2212.10474/) (2022)
- [Chinese Poetry Generation with Planning based Neural Network](https://mlsanity.com/paper/1610.09889/) (2016)
- [Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation](https://mlsanity.com/paper/2304.07854/) (2023)
- [Generating Chinese Classical Poems with RNN Encoder-Decoder](https://mlsanity.com/paper/1604.01537/) (2016)
- [Generating Major Types of Chinese Classical Poetry in a Uniformed Framework](https://mlsanity.com/paper/2003.11528/) (2020)
- [Flexible and Creative Chinese Poetry Generation Using Neural Memory](https://mlsanity.com/paper/1705.03773/) (2017)
- [Chinese Poetry Generation with a Working Memory Model](https://mlsanity.com/paper/1809.04306/) (2018)

## Built on by (most cited first, 18 of 18)

- [RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery](https://mlsanity.com/paper/2503.00751/) (2025)
- [Sonnet or Not, Bot? Poetry Evaluation for Large Models and Datasets](https://mlsanity.com/paper/2406.18906/) (2024)
- [Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability](https://mlsanity.com/paper/2506.15629/) (2025)
- [Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2508.21365/) (2025)
- [Can Agents Spontaneously Form a Society? Introducing a Novel Architecture for Generative Multi-Agents to Elicit Social Emergence](https://mlsanity.com/paper/2409.06750/) (2024)
- [PoeTone: A Framework for Constrained Generation of Structured Chinese Songci with LLMs](https://mlsanity.com/paper/2508.02515/) (2025)
- [What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking](https://mlsanity.com/paper/2509.04791/) (2025)
- [POEMetric: The Last Stanza of Humanity](https://mlsanity.com/paper/2604.03695/) (2026)
- [MetricalARGS: A Taxonomy for Studying Metrical Poetry with LLMs](https://mlsanity.com/paper/2510.08188/) (2025)
- [Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry](https://mlsanity.com/paper/2604.10101/) (2026)
- [How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them](https://mlsanity.com/paper/2604.17105/) (2026)
- [Instruction-Guided Poetry Generation in Arabic and Its Dialects](https://mlsanity.com/paper/2604.27766/) (2026)
- [Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese](https://mlsanity.com/paper/2606.07300/) (2026)
- [Do Large Language Models Perform Well on Comprehending Poetic Logic in Modern Chinese Poetry?](https://mlsanity.com/paper/2608.21827/) (2026)
- [Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement](https://mlsanity.com/paper/2608.23098/) (2026)
- [LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Space](https://mlsanity.com/paper/2608.23124/) (2026)
- [Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features](https://mlsanity.com/paper/2608.28986/) (2026)
- [Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry](https://mlsanity.com/paper/2609.19154/) (2026)

## Abstract (arXiv)

Automatic Chinese classical poetry generation has attracted much research interest, but achieving effective control over format and content simultaneously remains challenging. Traditional systems usually accept keywords as user inputs, resulting in limited control over content. Large language models (LLMs) improve content control by allowing unrestricted user instructions, but the token-by-token generation process frequently makes format errors. Motivated by this, we propose CharPoet, a Chinese classical poetry generation system based on token-free LLM, which provides effective control over both format and content. Our token-free architecture generates in a character-by-character manner, enabling precise control over the number of characters. Pruned from existing token-based LLMs, CharPoet inherits their pretrained capabilities and can generate poetry following instructions like "Write me a poem for my mother's birthday." CharPoet achieves format accuracy above 0.96, outperforming Jiuge-GPT-2 (0.91) and GPT-4 (0.38). In terms of content quality, CharPoet surpasses traditional systems including Jiuge, and is comparable to other LLMs. Our system is open source and available at https://modelscope.cn/models/CharPoet/CharPoet. A video demonstration of CharPoet is available at https://youtu.be/voZ25qEp3Dc.