PCcGE: Personalized Chinese Couplet Generation and Evaluation Framework Based on Large Language Models
Source abstract
Abstract
Couplets, consisting of a pair of clauses, are an important form of Chinese intangible cultural heritage, playing a significant role in the education and transmission of traditional Chinese culture. By engaging in couplet creation, students can enhance their Chinese comprehension and expression skills, literary creativity, and cultural identity. Personalized Chinese couplet (PCc) generation entails creating paired clauses that meet specific requirements while adhering to certain linguistic rules (e.g., morphological and syntactical symmetry). However, generating PCcs and evaluating the results is a challenging task that requires both cultural context and language understanding. Large Language Models (LLMs) have powerful learning and language comprehension abilities, providing new possibilities for addressing the challenges. In this study, we propose a framework for generating and evaluating PCcs using LLMs. First, we construct a couplet database, then use a retrieval method and design a specific prompt to provide a pair of clauses as references to guide the LLM following the rules of couplet style. Second, we construct a custom PCc generation dataset to train the base model, improving its ability for this task. Finally, we introduce a debate method based on LLMs to evaluate the quality of the generated couplets. By simulating adversarial human debate processes, it obtains more comprehensive and nuanced reference data for evaluation purposes. The experimental results show that our approach effectively generates and evaluates couplets. Reduced creation difficulty promotes couplet education and the preservation of Chinese intangible cultural heritage. Positive feedback from participants indicates that our framework can enhance user engagement, offer a positive PCc creation experience, and contribute to the education and transmission of couplet culture.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Computational and Text Analysis Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China
Funding
Jiangsu Provincial Key Laboratory of Culture and Tourism, China
References (43)
Show source-provided references
1. Gao, W. (2020). The Current Situation of Couplet Teaching in Primary School Classrooms and Attempts on Teaching Strategies. Educ. Art, 07, (In Chinese).
2. Sutskever, I. (2014). Sequence to Sequence Learning with Neural Networks. arXiv.
3. CoupGAN: Chinese couplet generation via encoder–decoder model and adversarial training under global control10.1007/s00500-021-06688-z ↗
4. Vaswani, A. (2017, January 4–9). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
5. Yan, R., Li, C.T., Hu, X., and Zhang, M. Chinese couplet generation with neural network structures. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
6. Chiang, K.Y., Lin, S., Chen, J., Yin, Q., and Jin, Q. (2021). Transcouplet: Transformer based chinese couplet generation. arXiv.
7. Song, Y. (2022, January 12–17). Chinese couplet generation with syntactic information. Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Republic of Korea.
8. Image based agorithm for automatic generation of chinese couplets
9. Papineni, K., Roukos, S., Ward, T., and Zhu, W.J. (2002, January 7–12). Bleu: A method for automatic evaluation of machine translation. Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, PA, USA.10.3115/1073083.1073135 ↗
10. Perplexity—A measure of the difficulty of speech recognition tasks10.1121/1.2016299 ↗
11. A survey on automatic generation of figurative language: From rule-based systems to large language models10.1145/3654795 ↗
12. Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Association for Computational Linguistics.
13. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., and Askell, A. (2020, January 6–12). Language models are few-shot learners. Proceedings of the Advances in Neural Information Processing Systems, Virtual.
14. Bai, J., Bai, S., Chu, Y., Cui, Z., Dang, K., Deng, X., Fan, Y., Ge, W., Han, Y., and Huang, F. (2023). Qwen technical report. arXiv.
15. Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., and Azhar, F. (2023). Llama: Open and efficient foundation language models. arXiv.
16. Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., and Anadkat, S. (2023). Gpt-4 technical report. arXiv.
17. Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., Zhao, C., Deng, C., Zhang, C., and Ruan, C. (2024). Deepseek-v3 technical report. arXiv.
18. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.t., and Rocktäschel, T. (2020, January 6–12). Retrieval-augmented generation for knowledge-intensive nlp tasks. Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, BC, Canada.
19. Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2021). Lora: Low-rank adaptation of large language models. arXiv.
20. Jiang, L., and Zhou, M. (2008, January 18–22). Generating Chinese couplets using a statistical MT approach. Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), Manchester, UK.10.3115/1599081.1599129 ↗
21. Zhou, M., Jiang, L., and He, J. (2009, January 3–5). Generating Chinese couplets and quatrain using a statistical approach. Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation, Hong Kong, China.
22. Zhang, J., Zhang, Z., Zhang, S., and Wang, D. (2018, January 12–15). VV-Couplet: An open source Chinese couplet generation system. Proceedings of the 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Honolulu, HI, USA.10.23919/APSIPA.2018.8659474 ↗
23. Tian, H., Yang, K., Liu, D., and Lv, J. (2021, January 18–22). Anchibert: A pre-trained model for ancient chinese language understanding and generation. Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Virtual.10.1109/IJCNN52387.2021.9534342 ↗
24. Encoder–Decoder Couplet Generation Model Based on ‘Trapezoidal Context’ Character Vector10.1093/comjnl/bxaa048 ↗
25. Transformer couplet generation model based on joint word segmentation
26. Research and implementation of Chinese couplet generation system with attention-based transformer mechanism10.1109/TCSS.2021.3072153 ↗
27. Zhang, R., and Eger, S. (2024). LLM-based multi-agent poetry generation in non-cooperative environments. arXiv.
28. Hu, Z., Liu, C., Feng, Y., Luu, A.T., and Hooi, B. (2024, January 20–28). Poetrydiffusion: Towards joint semantic and metrical manipulation in poetry generation. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.10.1609/aaai.v38i16.29787 ↗
29. Yu, C., Zang, L., Wang, J., Zhuang, C., and Gu, J. (2024). Charpoet: A chinese classical poetry generation system based on token-free llm. arXiv.10.18653/v1/2024.acl-demos.30 ↗
30. He, J., Zhou, M., and Jiang, L. (2012, January 22–26). Generating chinese classical poems with statistical machine translation models. Proceedings of the AAAI Conference on Artificial Intelligence, Toronto, ON, Canada.
31. Fan, H., Wang, J., Zhuang, B., Wang, S., and Xiao, J. (2019, January 26–30). Automatic acrostic couplet generation with three-stage neural network pipelines. Proceedings of the PRICAI 2019: Trends in Artificial Intelligence: 16th Pacific Rim International Conference on Artificial Intelligence, Cuvu, Fiji. Proceedings, Part I 16.10.1007/978-3-030-29908-8_25 ↗
32. Celikyilmaz, A., Clark, E., and Gao, J. (2020). Evaluation of text generation: A survey. arXiv.
33. Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., and Metzler, D. (2022). Emergent abilities of large language models. arXiv.
34. Parameter-efficient fine-tuning of large-scale pre-trained language models10.1038/s42256-023-00626-4 ↗
35. Marvin, G., Hellen, N., Jjingo, D., and Nakatumba-Nabende, J. (2023, January 27–28). Prompt engineering in large language models. Proceedings of the International Conference on Data Intelligence and Cognitive Informatics, Tirunelveli, India.10.1007/978-981-99-7962-2_30 ↗
36. Wong, M.F., and Tan, C.W. (2024). Aligning Crowd-Sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models. IEEE Trans. Big Data.10.1109/TBDATA.2024.3524104 ↗
37. Gao, S., Gao, C., Gu, W., and Lyu, M. (May, January 26). Search-based llms for code optimization. Proceedings of the 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE), Ottawa, ON, Canada.
38. Zhu, Z., Wu, Y., Gu, Q., and Cevher, V. (2024, January 9–15). Imbalance-Regularized LoRA: A Plug-and-Play Method for Improving Fine-Tuning of Foundation Models. Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024), Vancouver, BC, Canada.
39. Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., and Chen, Y. (2023). Siren’s song in the AI ocean: A survey on hallucination in large language models. arXiv.
40. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., and Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv.
41. Liang, T., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., Yang, Y., Shi, S., and Tu, Z. (2024, January 12–16). Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, FL, USA.10.18653/v1/2024.emnlp-main.992 ↗
42. Mohr, I., Krimmel, M., Sturua, S., Akram, M.K., Koukounas, A., Günther, M., Mastrapas, G., Ravishankar, V., Martínez, J.F., and Wang, F. (2024). Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings. arXiv.
43. Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., and Wei, H. (2024). Qwen2.5 Technical Report. arXiv.