Abstract
Human writing often exhibits a variety of styles and levels of sophistication, yet automated text generation systems typically struggle to produce nuanced and culturally sensitive prose. Achieving a balance between AI-driven automated generation and human judgment is essential for refining text in ways that respect diverse cultural contexts. This study addresses the challenges inherent in text refinement, a task that is complex due to the one-to-many relationship between inputs and outputs in natural language generation, making annotation consistency difficult. Our research proposes a semi-automatic data construction method that combines the strengths of both AI and human judgment to generate more elegant expressions while preserving the original semantics and cultural relevance of the input sentences. Initially, the method employs back translation to convert elegant expressions into more neutral ones, followed by an iterative quality control process. This process involves data filtering and human judgment to ensure that the automated generated text adheres to cultural norms and quality standards. By involving minimal human effort in each iteration, this approach significantly reduces the annotation workload while producing a large-scale, high-quality dataset for text refinement. Ultimately, this method contributes to the development of more culturally aware AI systems that facilitate ethical and effective intercultural communication in the age of globalization.
Data availability
Data will be made available upon reasonable request. Access requests should be directed to Dr. Yicheng Sun, subject to ethical approval and data protection requirements.No datasets were generated or analyzed during the current study.
References
Al Farisi MZ, Maulani H (2024) Machine translation shifts on the meaning equivalence of culture sentence and illocutionary speech acts: Back-translation. CaLLs J Cult Arts Lit Linguist 10(1):1–16
Almahameed Y (2020) A stylistic analysis of the short story The Little Match Girl. Int J Innov Creat Change 14(12):1229–1240
Barnes AJ, Zhang Y, Valenzuela A (2024) AI and culture: culturally dependent responses to AI systems. Curr Opin Psychol 58:101838
Bautista D, Atienza R (2022) Scene text recognition with permuted autoregressive sequence models. In European conference on computer vision Cham. Springer Nature, Switzerland, pp 178–196
Behr D (2017) Assessing the use of back translation: the shortcomings of back translation as a quality testing method. Int J Soc Res Methodol 20(6):573–584
Bonaldi H, Chung Y-L, Abercrombie G, Guerini M (2024) NLP for counterspeech against hate: a survey and how-to guide. In Findings of the Association for Computational Linguistics: NAACL 2024. Association for Computational Linguistics, Mexico City, Mexico, pp 3480–3499
Chowdhary K (2020) Natural language processing. In Fundamentals of artificial intelligence. New Delhi, India, Springer, pp 603–649
Cui Y, Che W, Liu T, Qin B, Wang S, Hu G (2020) Revisiting pre-trained models for Chinese natural language processing. In Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, Stroudsburg, PA, USA, pp 657–668
Desmond M, Duesterwald E, Brimijoin K, Brachman M, Pan Q (2021) Semi-automated data labeling. In NeurIPS 2020 competition and demonstration track. PMLR, pp 156–169
Devlin J, Chang M-W, Lee K, Toutanova K (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the Association for Computational Linguistics: human language technologies, Minneapolis, MN, US Volume 1 (long and short papers). Association for Computational Linguistics, Minneapolis, MN, USA, pp 4171–4186
Duch W (2000) Similarity-based methods: a general framework for classification, approximation and association. Control and Cybernetics 29(4):937–967
Frontull S, Moser G (2024) Rule-based, neural and LLM back-translation: Comparative insights from a variant of Ladin. In Proceedings of the seventh workshop on technologies for machine translation of low-resource languages (LoResMT 2024). Association for Computational Linguistics, Bangkok, Thailand, pp 128–138
Gao G, Taymanov A, Salinas E, Mineiro P, Misra D (2024a) Aligning LLM agents by learning latent preference from user edits. In Advances in neural information processing systems, vol 37. pp 136873–136896
Gao P, Sun N, Wang X, Yang C, Zitikis R (2024b) Natural language processing-based detection of systematic anomalies among the narratives of consumer complaints. J Operation Risk 19(2):79–104
Ghaddar A, Wu Y, Bagga S, Rashid A, Bibi K, Rezagholizadeh M et al. (2022) Revisiting pre-trained language models and their evaluation for Arabic natural language processing. In: Proceedings of the 2022 conference on empirical methods in natural language processing. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, pp 3135–3151
Gu Y, Zhang Z, Wang X, Liu Z, Sun M (2020) Train no evil: selective masking for task-guided pre-training. In Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP). Online: Association for Computational Linguistics, pp 6966–6974
Guo Q, Cao J, Xie X, Liu S, Li X, Chen B et al. (2024) Exploring the potential of ChatGPT in automated code refinement: an empirical study. In: Proceedings of the 46th IEEE/ACM international conference on software engineering. IEEE Computer Society / ACM Lisbon, Portugal, pp 1–13
Heelas P (2024) Emotion talk across cultures. In H. Wulff (Ed.), The Emotions. London, UK: Routledge pp 31–36
Hong K, Han L, Batista-Navarro RT, Nenadic G (2024) Cantonmt: Cantonese to english nmt platform with fine-tuned models using real and synthetic back-translation data. In Proceedings of the 25th annual conference of the European Association for Machine Translation, vol 1. Oxford University Press New York, NY, USA, pp 590–599
Hu S, Ding N, Wang H, Liu Z, Wang J, Li J et al. (2022) Knowledgeable prompt-tuning: Incorporating knowledge into prompt verbalizer for text classification. In: Proceedings of the 60th annual meeting of the Association for Computational Linguistics, vol 1: long papers. Association for Computational Linguistics, Dublin, Ireland, pp 2225–2240
Jin D, Jin Z, Hu Z, Vechtomova O, Mihalcea R (2022) Deep learning for text style transfer: a survey. Comput Linguist 48(1):155–205
Kang Y, Cai Z, Tan C-W, Huang Q, Liu H (2020) Natural language processing (nlp) in management research: a literature review. J Manag Anal 7(2):139–172
Kashyap K, Sarma SK, Ahmed MA (2024) Improving translation between English, Assamese bilingual pair with monolingual data, length penalty and model averaging. Int J Inf Technol 16(3):1539–1549
Katinskaia A, Yangarber R (2021) Assessing grammatical correctness in language learning. In Proceedings of the 16th workshop on innovative use of NLP for building educational applications. Online: Association for Computational Linguistics pp 135–146
Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O et al. (2020) Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th annual meeting of the Association for Computational Linguistics. Online: Association for Computational Linguistics pp 7871–7880
Li J, Galley M, Brockett C, Gao J, Dolan WB (2016) A diversity-promoting objective function for neural conversation models. In: Proceedings of the 2016 conference of the North American chapter of the Association for Computational Linguistics: human language technologies. Association for Computational Linguistics San Diego, CA, USA, pp 110–119
Li S, Kou P, Ma M, Yang H, Huang S, Yang Z (2024) Application of semi-supervised learning in image classification: research on fusion of labeled and unlabeled data. IEEE Access 12:27331–27343
Liu C-W, Lowe R, Serban IV, Noseworthy M, Charlin L, Pineau J (2016) How not to evaluate your dialogue system: an empirical study of unsupervised evaluation metrics for dialogue response generation. In Proceedings of the 2016 conference on empirical methods in natural language processing. Association for Computational Linguistics. Austin, TX, USA, pp 2122–2132
Lu Z, Zhou A, Ren H, Wang K, Shi W, Pan J et al. (2024) Mathgenie: generating synthetic data with question back-translation for enhancing mathematical reasoning of LLMs. In Proceedings of the 62nd annual meeting of the Association for Computational Linguistics, vol 1: Long Papers. pp 2732–2747
Ma D, Akram H, Chen I-H (2024) Artificial intelligence in higher education: a cross-cultural examination of students’ behavioral intentions and attitudes. Int Rev Res Open Distrib Learn 25(3):134–157
Madaan A, Tandon N, Gupta P, Hallinan S, Gao L, Wiegreffe S (2023) Self-refine: iterative refinement with self-feedback. In: Advances in neural information processing systems, vol 36. New Orleans, LA, USA: Curran Associates, Inc. pp 46534–46594
Madaan A, Tandon N, Gupta P, Hallinan S, Gao L, Wiegreffe S et al. (2024) Self-refine: iterative refinement with self-feedback. In: Advances in neural information processing systems, vol 36. Curran Associates, Inc. New Orleans, LA, USA
Maharana K, Mondal S, Nemade B (2022) A review: data pre-processing and data augmentation techniques. Glob Transit Proc 3(1):91–99
Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems, vol 26. Neural Information Processing Systems Foundation, Inc. / Curran Associates, Inc. Lake Tahoe, NV, USA
Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). Association for Computational Linguistics. Doha, Qatar, pp 1532–1543
Prabhumoye S, Tsvetkov Y, Salakhutdinov R, Black AW (2018) Style transfer through back-translation. In Proceedings of the 56th annual meeting of the Association for Computational Linguistics, vol 1: Long Papers. Association for Computational Linguistics Melbourne, Australia, pp 866–876
Radford A, Narasimhan K, Salimans T, Sutskever I (2018) Improving language understanding by generative pre-training (Technical report). OpenAI. https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf
Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21(140):1–67
Ren H, Li Z, Cai Y, Tan X, Wu X (2023) Learning refined features for open-world text classification with class description and commonsense knowledge. World Wide Web 26(2):637–660
Saha D, Tarek S, Yahyaei K, Saha SK, Zhou J, Tehranipoor M et al. (2024) LLM for soc security: a paradigm shift. IEEE Access, 12:155498–155521
Sennrich R, Haddow B, Birch A (2016) Improving neural machine translation models with monolingual data. In: Proceedings of the 54th annual meeting of the Association for Computational Linguistics, vol 1: long papers. Association for Computational Linguistics pp 86–96
Sun Y, Yang H, Yu HK, Suen R (2025) Boon or bane? evaluating AI-driven learning assistance in higher education professional coursework. Educ Inf Technol 30(15):22011–22044
Sun Y, Wang Y, Yang H, Suen R (2026) Adaptive template-based caching and LLM-driven summarization for richer student feedback insights. Educ Technol Soc 29(1):42–59
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In Advances in neural information processing systems, vol 27. Neural Information Processing Systems Foundation, Inc. Curran Associates, Inc, Montreal, QC, Canada
Veyseh A, Dernoncourt F, Dou D, Nguyen T (2020) A joint model for definition extraction with syntactic connection and semantic consistency. In: Proceedings of the AAAI conference on artificial intelligence, vol 34. pp 9098–9105. New York, NY, USA: AAAI Press
Xia Y, Shin S-Y, Kim J-C (2024) Cross-cultural intelligent language learning system (CILS): leveraging AI to facilitate language learning strategies in cross-cultural communication. Appl Sci 14(13):5651
Xu X, Zhang Z, Wang Z, Price B, Wang Z, Shi H (2021) Rethinking text segmentation: a novel dataset and a text-specific refinement approach. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. IEEE Computer Society / Computer Vision Foundation Nashville, TN, USA, pp 12045–12055
Yalcin S (2014) Semantics and metasemantics in the context of generative grammar. In: Metasemantics: new essays on the foundations of meaning, vol 17. Oxford University Press New York, NY, USA, pp 17–54
Zhang T, Kishore V, Wu F, Weinberger KQ, Artzi Y (2019) Bertscore: evaluating text generation with Bert. In International conference on learning representations. New Orleans, LA, USA: OpenReview.net
Zhao J, Huang C, Li X (2024) A comparative study of cultural hallucination in large language models on culturally specific ethical questions
Ziemski M, Junczys-Dowmunt M, Pouliquen B (2016) The United Nations parallel corpus v1.0. In: Calzolari N, Choukri K, Declerck T, Goggi S, Grobelnik M, Maegaard B et al. (eds) Proceedings of the tenth international conference on language resources and evaluation (LREC’16). European Language Resources Association (ELRA), Portorož, Slovenia, pp 3530–3534
Zlibrary (2024) Zlibrary: free online digital library of books and articles. https://z-lib.fm/. Accessed Jan 2025
Author information
Authors and Affiliations
Contributions
YS conceptualized the study and led the data collection process. YS and HY conducted the experiments and contributed to the data analysis. YS wrote the main manuscript text. YW and RS prepared all figures. All authors reviewed and approved the final manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
This study was reviewed and approved by the Institutional Review Board (IRB) of Shenzhen MSU-BIT University, which serves as the official ethics approval body for research involving human participants. Ethical approval was formally granted on 15 March 2024, under approval number 2024-03-017. All research procedures involving human participants were conducted in strict accordance with the ethical standards of the approving institution and relevant national research committees, as well as with the principles of the Declaration of Helsinki (1964) and its later amendments. The ethics review covered the use of human judgment in data quality assessment, expert evaluation of text-refinement outputs, and the authorized use of anonymized textual materials obtained from institutional repositories and licensed digital collections.
Informed consent
Informed consent was obtained from all human participants involved in this study prior to their participation. Consent procedures were conducted between April 2024 and July 2024, corresponding to the period of human judgment, expert evaluation, and validation activities reported in this paper. All participants were fully informed about the purpose of the research, the nature of the evaluation tasks, the voluntary nature of participation, and their right to withdraw at any time without penalty. Written informed consent was obtained before data collection commenced.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Sun, Y., Yang, H., Wang, Y. et al. Bridging human judgment and AI precision: a step toward intercultural competence in text refinement. Humanit Soc Sci Commun (2026). https://doi.org/10.1057/s41599-026-06593-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1057/s41599-026-06593-6
