Model and Evaluation: Towards Fairness in Multilingual Text Classification

preprint OA: closed CC-BY-4.0
📄 Open PDF Full text JSON View at publisher

Abstract

Abstract Recently, more and more research has focused on addressing bias in text classification models. However, existing research mainly focuses on the fairness of monolingual text classification models, and research on fairness for multilingual text classification is still very limited. In this paper, we focus on the task of multilingual text classification and propose a debiasing framework for multilingual text classification based on contrastive learning. Our proposed method does not rely on any external language resources and can be extended to any other languages. In addition, the existing research on the fairness of multilingual text classification is relatively simple in the evaluation mode. The evaluation method of fairness is the same as the monolingual equality difference evaluation method, that is, the evaluation is performed on a single language. We propose a multi-dimensional fairness evaluation framework for multilingual text classification, which evaluates the model’s monolingual equality difference, multilingual equality difference, multilingual equality performance difference, and negative gain of the fairness strategy. We hope that our work can provide a more general debiasing method and a more comprehensive evaluation framework for multilingual text fairness tasks.
Full text 14,416 characters · extracted from preprint-html · click to expand
Model and Evaluation: Towards Fairness in Multilingual Text Classification | 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 Research Article Model and Evaluation: Towards Fairness in Multilingual Text Classification Nankai Lin, Junheng He, Zhenghang Tang, Jiajun Fang, Aimin Yang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5018458/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 Feb, 2026 Read the published version in International Journal of Machine Learning and Cybernetics → Version 1 posted 12 You are reading this latest preprint version Abstract Recently, more and more research has focused on addressing bias in text classification models. However, existing research mainly focuses on the fairness of monolingual text classification models, and research on fairness for multilingual text classification is still very limited. In this paper, we focus on the task of multilingual text classification and propose a debiasing framework for multilingual text classification based on contrastive learning. Our proposed method does not rely on any external language resources and can be extended to any other languages. In addition, the existing research on the fairness of multilingual text classification is relatively simple in the evaluation mode. The evaluation method of fairness is the same as the monolingual equality difference evaluation method, that is, the evaluation is performed on a single language. We propose a multi-dimensional fairness evaluation framework for multilingual text classification, which evaluates the model’s monolingual equality difference, multilingual equality difference, multilingual equality performance difference, and negative gain of the fairness strategy. We hope that our work can provide a more general debiasing method and a more comprehensive evaluation framework for multilingual text fairness tasks. Multilingual Text Classification Debiasing Framework Multi-dimensional Fairness Evaluation Framework Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 02 Feb, 2026 Read the published version in International Journal of Machine Learning and Cybernetics → Version 1 posted Editorial decision: Revision requested 28 May, 2025 Reviews received at journal 05 May, 2025 Reviewers agreed at journal 29 Apr, 2025 Reviews received at journal 23 Apr, 2025 Reviewers agreed at journal 26 Mar, 2025 Reviewers agreed at journal 08 Feb, 2025 Reviewers agreed at journal 08 Feb, 2025 Reviewers agreed at journal 14 Sep, 2024 Reviewers invited by journal 09 Sep, 2024 Editor assigned by journal 06 Sep, 2024 Submission checks completed at journal 04 Sep, 2024 First submitted to journal 02 Sep, 2024 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-5018458","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":353951598,"identity":"ac096d9d-7aac-4dce-a629-bb4c6272f5ee","order_by":0,"name":"Nankai Lin","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Nankai","middleName":"","lastName":"Lin","suffix":""},{"id":353951599,"identity":"23644941-8d5b-4a94-852a-ad3570249014","order_by":1,"name":"Junheng He","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Junheng","middleName":"","lastName":"He","suffix":""},{"id":353951600,"identity":"fb777a9b-4e2b-45ec-af73-a7edead2d63d","order_by":2,"name":"Zhenghang Tang","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhenghang","middleName":"","lastName":"Tang","suffix":""},{"id":353951602,"identity":"f9ad71c7-0a69-4007-8fde-ca2f26f380f3","order_by":3,"name":"Jiajun Fang","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jiajun","middleName":"","lastName":"Fang","suffix":""},{"id":353951604,"identity":"a7bad79c-257a-47b7-861f-1a6c8eda11dd","order_by":4,"name":"Aimin Yang","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Aimin","middleName":"","lastName":"Yang","suffix":""},{"id":353951606,"identity":"c5ff4a14-c291-49d4-860b-a86925b8bfc7","order_by":5,"name":"Dong Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYDCCA0DM2MDAwM/AYMBQARMhSotkA1DLGZK0GBwgVgvf8d7DL3/usEncfH7xNokDfxjk+G4kMH4uwKNF8sy5NAvJM2mJ2248K5M42MZgLHkjgVl6Bh4tBjdyzAwM2w4DtZwxk/7YwJC44UYCGzMPIS2JQC2bZ5wxAzmsnhgtxg8OArVs4O8BamFjSDAgpEXyzBkzxsa2NOMZN9iKLQ62SRjOPPOwWRqfFr7jPcYff7bZyPb3H95448AfG3m+48kHP+PTAgRsEmBKIgFMMkCiCT9g/gCm+A8QUjgKRsEoGAUjFQAAO6VZXiaYA/AAAAAASUVORK5CYII=","orcid":"","institution":"Guangdong University of Foreign Studies","correspondingAuthor":true,"prefix":"","firstName":"Dong","middleName":"","lastName":"Zhou","suffix":""}],"badges":[],"createdAt":"2024-09-02 12:48:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5018458/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5018458/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s13042-025-02824-5","type":"published","date":"2026-02-02T15:57:35+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":102234004,"identity":"b14e0d3a-8f60-439a-b73c-b2cc75348b3e","added_by":"auto","created_at":"2026-02-09 16:03:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":506791,"visible":true,"origin":"","legend":"","description":"","filename":"ModelandEvaluation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5018458/v1_covered_e2373a48-fc67-45a6-a9bc-e571a397222c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Model and Evaluation: Towards Fairness in Multilingual Text Classification","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":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Multilingual Text Classification, Debiasing Framework, Multi-dimensional Fairness Evaluation Framework","lastPublishedDoi":"10.21203/rs.3.rs-5018458/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5018458/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRecently, more and more research has focused on addressing bias in text classification models. However, existing research mainly focuses on the fairness of monolingual text classification models, and research on fairness for multilingual text classification is still very limited. In this paper, we focus on the task of multilingual text classification and propose a debiasing framework for multilingual text classification based on contrastive learning. Our proposed method does not rely on any external language resources and can be extended to any other languages. In addition, the existing research on the fairness of multilingual text classification is relatively simple in the evaluation mode. The evaluation method of fairness is the same as the monolingual equality difference evaluation method, that is, the evaluation is performed on a single language. We propose a multi-dimensional fairness evaluation framework for multilingual text classification, which evaluates the model\u0026rsquo;s monolingual equality difference, multilingual equality difference, multilingual equality performance difference, and negative gain of the fairness strategy. We hope that our work can provide a more general debiasing method and a more comprehensive evaluation framework for multilingual text fairness tasks.\u003c/p\u003e","manuscriptTitle":"Model and Evaluation: Towards Fairness in Multilingual Text Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-07 05:31:16","doi":"10.21203/rs.3.rs-5018458/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-28T07:14:33+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-05T11:39:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"235033201232887347281604010223882939705","date":"2025-04-29T17:24:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-24T02:33:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"150771285614075231046034359088821461292","date":"2025-03-26T14:56:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"87638579790973074824518362381598218015","date":"2025-02-08T05:42:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"268811941771466530078261168842271118325","date":"2025-02-08T05:04:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"284740493127683405808862474979221252067","date":"2024-09-14T08:16:09+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-09-09T07:57:18+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-09-06T07:13:38+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-09-04T10:02:12+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2024-09-02T12:47:00+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"8d3656d3-5a49-4693-ba1c-f541e1ff1cff","owner":[],"postedDate":"October 7th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-02-09T16:00:47+00:00","versionOfRecord":{"articleIdentity":"rs-5018458","link":"https://doi.org/10.1007/s13042-025-02824-5","journal":{"identity":"international-journal-of-machine-learning-and-cybernetics","isVorOnly":false,"title":"International Journal of Machine Learning and Cybernetics"},"publishedOn":"2026-02-02 15:57:35","publishedOnDateReadable":"February 2nd, 2026"},"versionCreatedAt":"2024-10-07 05:31:16","video":"","vorDoi":"10.1007/s13042-025-02824-5","vorDoiUrl":"https://doi.org/10.1007/s13042-025-02824-5","workflowStages":[]},"version":"v1","identity":"rs-5018458","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5018458","identity":"rs-5018458","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2024) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-05-28T02:00:01.590549+00:00
License: CC-BY-4.0