Mixture of Detectors: A Compact View of Machine-Generated Text Detection

Mixture of Detectors: A Compact View of Machine-Generated Text Detection | 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 Mixture of Detectors: A Compact View of Machine-Generated Text Detection Sai Teja Lekkala, Yadagiri Annepaka, Arun Kumar Challa, Samatha Reddy Machireddy, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7426641/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Large Language Models (LLMs) are gearing up to surpass human creativity. The veracity of the statement needs careful consideration. In recent developments, critical questions arise regarding the authenticity of human work and the preservation of their creativity and innovative abilities. This paper investigates such issues. This paper addresses machine-generated text detection across several scenarios, including document-level binary and multiclass classification or generator attribution, sentence-level segmentation to differentiate between human-AI collaborative text, and adversarial attacks aimed at reducing the detectability of machine-generated text. We introduce a new work called BMAS English: an English language dataset for binary classification of human and machine text, for multiclass classification, which not only identifies machine-generated text but can also try to determine its generator, and Adversarial attack addressing where it is a common act for the mitigation of detection, and Sentence-level segmentation, for predicting the boundaries between human and machine-generated text. We believe that this paper will address previous work in Machine-Generated Text Detection (MGTD) in a more meaningful way. Large language model Adversarial Attacks AI-generated Text detection Text classification Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 17 Mar, 2026 Reviews received at journal 17 Mar, 2026 Reviewers agreed at journal 05 Mar, 2026 Reviews received at journal 09 Nov, 2025 Reviewers agreed at journal 07 Oct, 2025 Reviewers invited by journal 07 Oct, 2025 Editor assigned by journal 29 Sep, 2025 Submission checks completed at journal 21 Aug, 2025 First submitted to journal 21 Aug, 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-7426641","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":531269019,"identity":"21a34b21-9061-4611-93e0-ea8c18e07557","order_by":0,"name":"Sai Teja Lekkala","email":"","orcid":"","institution":"National Institute Of Technology Silchar","correspondingAuthor":false,"prefix":"","firstName":"Sai","middleName":"Teja","lastName":"Lekkala","suffix":""},{"id":531269021,"identity":"9961df7d-ef28-476c-9f11-e96fd80cb412","order_by":1,"name":"Yadagiri Annepaka","email":"","orcid":"","institution":"National Institute Of Technology Silchar","correspondingAuthor":false,"prefix":"","firstName":"Yadagiri","middleName":"","lastName":"Annepaka","suffix":""},{"id":531269022,"identity":"facc743d-f49f-4ffc-bbba-a5f0372b3ea3","order_by":2,"name":"Arun Kumar Challa","email":"","orcid":"","institution":"National Institute Of Technology Silchar","correspondingAuthor":false,"prefix":"","firstName":"Arun","middleName":"Kumar","lastName":"Challa","suffix":""},{"id":531269023,"identity":"e9d2452d-4145-455e-adfb-f8b46fc1c9bb","order_by":3,"name":"Samatha Reddy Machireddy","email":"","orcid":"","institution":"National Institute Of Technology Silchar","correspondingAuthor":false,"prefix":"","firstName":"Samatha","middleName":"Reddy","lastName":"Machireddy","suffix":""},{"id":531269024,"identity":"35170877-a37b-4883-9dc1-7b6ab3b9a963","order_by":4,"name":"Partha Pakray","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5UlEQVRIiWNgGAWjYJACZgYGGwgrASpygIAOxmYGhjSolgTitRxmQLUGHzBnP/v8cUHNeXn59ga2Bw9/1DHwtx9gPFyAR4tlT7ph84xjtw03nDnAbpCQcJhB4kwCw+EZeLQYHEhjbOZhu51gIJHAJpGQAPTFDaA7efBpOf8MqOXfuQT5+Q9AWuoY5AlquQG0hbftQALQcJAWZqAIAS2WM54xzubtSwb6JbFNIiHtMI/hmcQGvFrM+dMYPvN8swOG2OFjkj9s6uTkjh8+/BmvwxBMxgYQyQNjEKNlFIyCUTAKRgEOAADiIknDRM4oFgAAAABJRU5ErkJggg==","orcid":"","institution":"National Institute Of Technology Silchar","correspondingAuthor":true,"prefix":"","firstName":"Partha","middleName":"","lastName":"Pakray","suffix":""},{"id":531269025,"identity":"0f9be8d1-6a16-4029-9918-37de819636ab","order_by":5,"name":"Chukhu Chunka","email":"","orcid":"","institution":"National Institute Of Technology Silchar","correspondingAuthor":false,"prefix":"","firstName":"Chukhu","middleName":"","lastName":"Chunka","suffix":""}],"badges":[],"createdAt":"2025-08-21 13:23:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7426641/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7426641/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93906346,"identity":"c5d6f421-ac31-4a73-b093-9800f9afc90e","added_by":"auto","created_at":"2025-10-20 07:13:05","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7139,"visible":true,"origin":"","legend":"","description":"","filename":"9aaaccbf55164259832e4cfd05ea0747.json","url":"https://assets-eu.researchsquare.com/files/rs-7426641/v1/b3e3350e1130008ebc2542f1.json"},{"id":93906997,"identity":"f573715e-93b0-409b-904c-b896eb16f425","added_by":"auto","created_at":"2025-10-20 07:21:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":925215,"visible":true,"origin":"","legend":"","description":"","filename":"MixtureofDetectorsACompactViewofMachineGeneratedTextDetection.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7426641/v1_covered_86de8597-d228-44ad-a98e-b5e012047655.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Mixture of Detectors: A Compact View of Machine-Generated Text Detection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Large language model, Adversarial Attacks, AI-generated Text detection, Text classification","lastPublishedDoi":"10.21203/rs.3.rs-7426641/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7426641/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Large Language Models (LLMs) are gearing up to surpass human creativity. The veracity of the statement needs careful consideration. In recent developments, critical questions arise regarding the authenticity of human work and the preservation of their creativity and innovative abilities. This paper investigates such issues. This paper addresses machine-generated text detection across several scenarios, including document-level binary and multiclass classification or generator attribution, sentence-level segmentation to differentiate between human-AI collaborative text, and adversarial attacks aimed at reducing the detectability of machine-generated text. We introduce a new work called BMAS English: an English language dataset for binary classification of human and machine text, for multiclass classification, which not only identifies machine-generated text but can also try to determine its generator, and Adversarial attack addressing where it is a common act for the mitigation of detection, and Sentence-level segmentation, for predicting the boundaries between human and machine-generated text. We believe that this paper will address previous work in Machine-Generated Text Detection (MGTD) in a more meaningful way.","manuscriptTitle":"Mixture of Detectors: A Compact View of Machine-Generated Text Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-20 07:13:01","doi":"10.21203/rs.3.rs-7426641/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-17T11:27:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-17T11:22:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"282743183178268596647639206538747906829","date":"2026-03-05T14:18:57+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-09T11:03:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"318021744129902910756512488268315094564","date":"2025-10-07T14:06:45+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-07T13:59:34+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-29T13:45:18+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-22T00:09:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"Language Resources and Evaluation","date":"2025-08-21T13:16:22+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a8c74581-754d-4041-bb70-250f08df602d","owner":[],"postedDate":"October 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-17T06:53:18+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-20 07:13:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7426641","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7426641","identity":"rs-7426641","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}