Balancing AI and Human Judgment for Text Refinement: A Step Toward Intercultural Competence in Language Processing

Balancing AI and Human Judgment for Text Refinement: A Step Toward Intercultural Competence in Language Processing | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Balancing AI and Human Judgment for Text Refinement: A Step Toward Intercultural Competence in Language Processing Yicheng Sun, Yi Wang, Hanbo Yang, Richard Suen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6024984/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Feb, 2026 Read the published version in Humanities and Social Sciences Communications → Version 1 posted 10 You are reading this latest preprint version 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 auto-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 auto-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. Humanities/Language and linguistics Social science/Language and linguistics Social science/Science technology and society Natural Language Process Human-Machine Collaboration Text Refinement Infilling Objective Paraphrase Objective Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 Feb, 2026 Read the published version in Humanities and Social Sciences Communications → Version 1 posted Editorial decision: Revision requested 01 Sep, 2025 Reviewers agreed at journal 09 Jun, 2025 Reviews received at journal 05 Jun, 2025 Reviewers agreed at journal 23 Apr, 2025 Reviews received at journal 27 Feb, 2025 Reviewers agreed at journal 26 Feb, 2025 Reviewers invited by journal 25 Feb, 2025 Editor assigned by journal 24 Feb, 2025 Submission checks completed at journal 19 Feb, 2025 First submitted to journal 13 Feb, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6024984","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":419880090,"identity":"0f2dfb07-70e2-456d-b07a-4981ad26a8f6","order_by":0,"name":"Yicheng Sun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEklEQVRIie2OMUvDQBiGvxLJFMn6TclfuBCoFv0xOQRdqm7BoWCnuBS6Hgj+AodMna8cxCWm6wkdKgEnhZQuXQQvucWhCRkF74G79+Pue+AFMBj+KhFwdVv815PdS7F1KLeHAs2uQ/opPrvOcDNZeyfu8263TYDO2S2HKhbgPk4PKkTeXGKUfYQj9rXAZQIhygsYsEIArvlhBcdDpFNBU/m6AKV4oBTrOBHqK2opppX7VOZlpRTHr5XvDgWkViKymkFdzCO1MuhQSP4ZnkaZCFJpDzEvMAzykixnxZWDsqXYwzh420+ET1airO7ic/r0Qt83+/jMc1lLMYAjbELX0DNXx2nbV1hVEy7v2DEYDIZ/zQ8+8GVghXkKBQAAAABJRU5ErkJggg==","orcid":"","institution":"Xi'an University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Yicheng","middleName":"","lastName":"Sun","suffix":""},{"id":419880091,"identity":"fb361bef-462a-43e6-89dc-18efdfaf29bc","order_by":1,"name":"Yi Wang","email":"","orcid":"","institution":"Xi'an University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yi","middleName":"","lastName":"Wang","suffix":""},{"id":419880092,"identity":"d767300a-5324-4d24-9620-b6d1a9fcdd03","order_by":2,"name":"Hanbo Yang","email":"","orcid":"","institution":"Xi'an University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Hanbo","middleName":"","lastName":"Yang","suffix":""},{"id":419880093,"identity":"d06d4c4c-295d-4f41-855e-cef3bd54ef43","order_by":3,"name":"Richard Suen","email":"","orcid":"","institution":"Shenzhen MSU-BIT University","correspondingAuthor":false,"prefix":"","firstName":"Richard","middleName":"","lastName":"Suen","suffix":""}],"badges":[],"createdAt":"2025-02-13 17:23:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6024984/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6024984/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1057/s41599-026-06593-6","type":"published","date":"2026-02-03T15:57:52+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":102235874,"identity":"c794a4c5-1eee-4ea9-b236-ab81e774e2c6","added_by":"auto","created_at":"2026-02-09 16:18:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3696002,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6024984/v1_covered_da771d5b-38f6-416c-a460-b0caa690b3b9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Balancing AI and Human Judgment for Text Refinement: A Step Toward Intercultural Competence in Language Processing","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"humanities-and-social-sciences-communications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"palcomms","sideBox":"Learn more about [Humanities \u0026 Social Sciences Communications](http://www.nature.com/palcomms/)","snPcode":"41599","submissionUrl":"https://submission.springernature.com/new-submission/41599/3","title":"Humanities and Social Sciences Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Nature AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Natural Language Process, Human-Machine Collaboration, Text Refinement, Infilling Objective, Paraphrase Objective","lastPublishedDoi":"10.21203/rs.3.rs-6024984/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6024984/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"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 auto-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 auto-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.","manuscriptTitle":"Balancing AI and Human Judgment for Text Refinement: A Step Toward Intercultural Competence in Language Processing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-24 06:48:27","doi":"10.21203/rs.3.rs-6024984/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-01T17:56:29+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"16594779146912351737332141043799912156","date":"2025-06-09T12:53:03+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-05T09:50:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"315017701383663193482886064750007124285","date":"2025-04-23T16:04:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-27T09:48:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"256744793616100647307417699724155522544","date":"2025-02-26T14:34:02+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-02-25T16:37:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-02-24T09:06:05+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-02-19T19:51:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"Humanities and Social Sciences Communications","date":"2025-02-13T17:09:06+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"humanities-and-social-sciences-communications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"palcomms","sideBox":"Learn more about [Humanities \u0026 Social Sciences Communications](http://www.nature.com/palcomms/)","snPcode":"41599","submissionUrl":"https://submission.springernature.com/new-submission/41599/3","title":"Humanities and Social Sciences Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Nature AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f8997415-8c83-4388-8e9e-76a3f58ac95f","owner":[],"postedDate":"February 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":44758931,"name":"Humanities/Language and linguistics"},{"id":44758932,"name":"Social science/Language and linguistics"},{"id":44758933,"name":"Social science/Science technology and society"}],"tags":[],"updatedAt":"2026-02-09T16:17:46+00:00","versionOfRecord":{"articleIdentity":"rs-6024984","link":"https://doi.org/10.1057/s41599-026-06593-6","journal":{"identity":"humanities-and-social-sciences-communications","isVorOnly":false,"title":"Humanities and Social Sciences Communications"},"publishedOn":"2026-02-03 15:57:52","publishedOnDateReadable":"February 3rd, 2026"},"versionCreatedAt":"2025-02-24 06:48:27","video":"","vorDoi":"10.1057/s41599-026-06593-6","vorDoiUrl":"https://doi.org/10.1057/s41599-026-06593-6","workflowStages":[]},"version":"v1","identity":"rs-6024984","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6024984","identity":"rs-6024984","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}