EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Heterogeneous Text Style Control Using Prompts

Yafu Li, Jiahao Gai, Yongjing Yin, Jianhao Yan, Yue Zhang

ACM Transactions on Asian and Low-Resource Language Information Processing · 30.06.2026 · 25 (6) · 1-21

DOI: 10.1145/3806042 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Asian and Low-Resource Language Information Processing, online erschienen am 08.06.2026. Verfasst von Yafu Li und 4 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Technology of China, Zhejiang Province Key Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advancements in natural language processing (NLP) have markedly improved paraphrase generation, an essential task for numerous applications. However, current methods face limitations due to model and constraint specificity, which hinder their flexibility and practical deployment. In this work, we introduce a unified prompt-driven approach to paraphrase generation that leverages diverse prompts, enabling fine-grained user control over aspects such as syntax and sentiment. Moreover, we incorporate translation to enable sophisticated cross-lingual text controls. Our system employs a data-centric paradigm which organizes prompts with natural language instructions. The proposed method is compatible with various sequence-to-sequence architectures and utilizes a novel training strategy to address the versatility of prompt combinations. Empirical results show that our approach not only demonstrates its capacity to adhere to multiple user-defined constraints but also maintains high performance in generation tasks without prompts. Moreover, extensive analysis shows that the model exhibits robustness to prompt variance such as language and quantity.

Förderung

  • Ministry of Science and Technology of China
  • Zhejiang Province Key Project

Zitieren

APA

Li, Y., Gai, J., Yin, Y., Yan, J., & Zhang, Y. (2026). Heterogeneous Text Style Control Using Prompts. ACM Transactions on Asian and Low-Resource Language Information Processing, 25(6), 1-21. https://doi.org/10.1145/3806042

Vancouver

Li Y, Gai J, Yin Y, Yan J, Zhang Y. Heterogeneous Text Style Control Using Prompts. ACM Transactions on Asian and Low-Resource Language Information Processing. 2026;25(6):1-21. doi:10.1145/3806042

BibTeX
@article{Li2026,
  author = {Li, Yafu and Gai, Jiahao and Yin, Yongjing and Yan, Jianhao and Zhang, Yue},
  title = {Heterogeneous Text Style Control Using Prompts},
  journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
  year = {2026},
  volume = {25},
  number = {6},
  pages = {1--21},
  doi = {10.1145/3806042}
}
Kostenlos starten →