{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T12:04:22Z","timestamp":1780920262534,"version":"3.54.1"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:00:00Z","timestamp":1780876800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Ministry of Science and Technology of China","award":["2022YFE0204900"],"award-info":[{"award-number":["2022YFE0204900"]}]},{"name":"Zhejiang Province Key Project","award":["2022SDXHDX0003"],"award-info":[{"award-number":["2022SDXHDX0003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1145\/3806042","type":"journal-article","created":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T10:34:39Z","timestamp":1776162879000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Heterogeneous Text Style Control Using Prompts"],"prefix":"10.1145","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7895-9997","authenticated-orcid":false,"given":"Yafu","family":"Li","sequence":"first","affiliation":[{"name":"Westlake University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9714-1565","authenticated-orcid":false,"given":"Jiahao","family":"Gai","sequence":"additional","affiliation":[{"name":"Cambridge University","place":["Cambridge, United Kingdom of Great Britain and Northern Ireland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1138-4612","authenticated-orcid":false,"given":"Yongjing","family":"Yin","sequence":"additional","affiliation":[{"name":"Westlake University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2895-1822","authenticated-orcid":false,"given":"Jianhao","family":"Yan","sequence":"additional","affiliation":[{"name":"Westlake University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5214-2268","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for Advanced Study, Westlake University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.45"},{"key":"e_1_3_2_3_2","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et\u00a0al. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"e_1_3_2_4_2","first-page":"12630","volume-title":"Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021","author":"Chen Guanhua","year":"2021","unstructured":"Guanhua Chen, Yun Chen, and Victor O. K. Li. 2021. Lexically constrained neural machine translation with explicit alignment guidance. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021. AAAI Press, 12630\u201312638. Retrieved from https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17496"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/496"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/496"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1599"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma et\u00a0al. 2022. Scaling Instruction-Finetuned Language Models. DOI:10.48550\/ARXIV.2210.11416","DOI":"10.48550\/ARXIV.2210.11416"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1294"},{"key":"e_1_3_2_10_2","first-page":"644","volume-title":"Proc. of NAACL-HLT","author":"Dyer Chris","year":"2013","unstructured":"Chris Dyer, Victor Chahuneau, and Noah A. Smith. 2013. A simple, fast, and effective reparameterization of IBM model 2. In Proc. of NAACL-HLT. Association for Computational Linguistics, Atlanta, Georgia, 644\u2013648. Retrieved from https:\/\/aclanthology.org\/N13-1073"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.60"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1141"},{"key":"e_1_3_2_13_2","series-title":"Proceedings of Machine Learning Research","first-page":"1587","volume-title":"Proc. of ICML","volume":"70","author":"Hu Zhiting","year":"2017","unstructured":"Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P. Xing. 2017. Toward controlled generation of text. In Proc. of ICML(Proceedings of Machine Learning Research, Vol. 70). Doina Precup and Yee Whye Teh (Eds.). PMLR, 1587\u20131596. Retrieved from http:\/\/proceedings.mlr.press\/v70\/hu17e.html"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1170"},{"key":"e_1_3_2_15_2","article-title":"Is ChatGPT a good translator? Yes with GPT-4 as the engine","volume":"2301","author":"Jiao Wenxiang","year":"2023","unstructured":"Wenxiang Jiao, Wenxuan Wang, JT Huang, Xing Wang, and ZP Tu. 2023. Is ChatGPT a good translator? Yes with GPT-4 as the engine. ArXiv preprint abs\/2301.08745 (2023). https:\/\/arxiv.org\/abs\/2301.08745","journal-title":"ArXiv preprint"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.311"},{"key":"e_1_3_2_17_2","volume-title":"Proc. of ICLR","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proc. of ICLR, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00318"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1363"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.788"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.203"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5829"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2050"},{"key":"e_1_3_2_24_2","first-page":"8568","volume-title":"The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020","author":"Niu Xing","year":"2020","unstructured":"Xing Niu and Marine Carpuat. 2020. Controlling neural machine translation formality with synthetic supervision. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020. AAAI Press, 8568\u20138575. Retrieved from https:\/\/aaai.org\/ojs\/index.php\/AAAI\/article\/view\/6379"},{"key":"e_1_3_2_25_2","article-title":"GPT-4 Technical Report","volume":"2303","year":"2023","unstructured":"OpenAI. 2023. GPT-4 Technical Report. ArXiv preprint abs\/2303.08774 (2023). https:\/\/arxiv.org\/abs\/2303.08774","journal-title":"ArXiv preprint"},{"key":"e_1_3_2_26_2","volume-title":"NeurIPS","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et\u00a0al. 2022. Training language models to follow instructions with human feedback. In NeurIPS."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1119"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"e_1_3_2_31_2","article-title":"Is ChatGPT a general-purpose natural language processing task solver?","volume":"2302","author":"Qin Chengwei","year":"2023","unstructured":"Chengwei Qin, Aston Zhang, Zhuosheng Zhang, Jiaao Chen, Michihiro Yasunaga, and Diyi Yang. 2023. Is ChatGPT a general-purpose natural language processing task solver? ArXiv preprint abs\/2302.06476 (2023). https:\/\/arxiv.org\/abs\/2302.06476","journal-title":"ArXiv preprint"},{"key":"e_1_3_2_32_2","unstructured":"Qwen : An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu et\u00a0al. 2025. Qwen2.5 Technical Report. arxiv:2412.15115 [cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_33_2","first-page":"1074","volume-title":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers","author":"Rabinovich Ella","year":"2017","unstructured":"Ella Rabinovich, Raj Nath Patel, Shachar Mirkin, Lucia Specia, and Shuly Wintner. 2017. Personalized machine translation: preserving original author traits. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. Association for Computational Linguistics, Valencia, Spain, 1074\u20131084. Retrieved from https:\/\/aclanthology.org\/E17-1101"},{"issue":"8","key":"e_1_3_2_34_2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9.","journal-title":"OpenAI blog"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1005"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_37_2","first-page":"6830","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA","author":"Shen Tianxiao","year":"2017","unstructured":"Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi S. Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 6830\u20136841. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/2d2c8394e31101a261abf1784302bf75-Abstract.html"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1044"},{"key":"e_1_3_2_39_2","first-page":"38","volume-title":"Proc. of ACL","author":"Sun Hong","year":"2012","unstructured":"Hong Sun and Ming Zhou. 2012. Joint learning of a dual SMT system for paraphrase generation. In Proc. of ACL. Association for Computational Linguistics, Jeju Island, Korea, 38\u201342. Retrieved from https:\/\/aclanthology.org\/P12-2008"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.420"},{"key":"e_1_3_2_41_2","unstructured":"Rohan Taori Ishaan Gulrajani Tianyi Zhang Yann Dubois Xuechen Li Carlos Guestrin Percy Liang and Tatsunori B. Hashimoto. 2023. Stanford Alpaca: An Instruction-following LLaMA model. Retrieved from https:\/\/github.com\/tatsu-lab\/stanford_alpaca"},{"key":"e_1_3_2_42_2","article-title":"Llama 2: Open foundation and fine-tuned chat models","volume":"2307","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. ArXiv preprint abs\/2307.09288 (2023). https:\/\/arxiv.org\/abs\/2307.09288","journal-title":"ArXiv preprint"},{"key":"e_1_3_2_43_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998\u20136008. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3806042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T11:26:33Z","timestamp":1780917993000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3806042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,8]]},"references-count":43,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3806042"],"URL":"https:\/\/doi.org\/10.1145\/3806042","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,8]]},"assertion":[{"value":"2024-07-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}