MOJO: Multi-LLM Optimised Joint Objective - Generative Artificial Intelligence for Multi-Criteria Decision Analysis Framework

MOJO: Multi-LLM Optimised Joint Objective - Generative Artificial Intelligence for Multi-Criteria Decision Analysis Framework | 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 MOJO: Multi-LLM Optimised Joint Objective - Generative Artificial Intelligence for Multi-Criteria Decision Analysis Framework Abtin Ijadi Maghsoodi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8755908/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract This study introduces the Multi-LLM Optimised Joint Objective (MOJO), a novel generative artificial intelligence (Gen-AI) driven multi-criteria decision analysis (MCDA) framework. MOJO uniquely integrates human expertise with multiple large language models (LLMs) to address limitations in traditional MCDA approaches. The information fusion framework combines risk-adjusted utility scoring, performance equilibrium, and reliability scoring, producing consensus-driven rankings that effectively account for uncertainty and non-linear risk preferences. Grounded in principles from prospect theory and utility theory, MOJO captures complex behavioural factors such as loss aversion and probability distortion. An ensemble of LLM outputs automates MCDA tasks, enhanced by systematic bias correction to reduce cognitive load and improve transparency. MOJO also incorporates a comprehensive illustrative case study evaluating treatments for Inflammatory Bowel Disease (IBD), demonstrating its applicability to complex scenarios involving clinical, operational, and ethical criteria. Results from validation experiments involving multiple LLMs and decision-makers across diverse scenarios highlight MOJO's robustness, reliability, and transparency, demonstrating its significant potential in high-stakes fields such as healthcare, engineering, and public policy. Multi-Criteria Decision Analysis (MCDA) Large Language Model (LLM) Artificial Intelligence Generative AI (Gen-AI) Decision Bias Full Text Additional Declarations No competing interests reported. Supplementary Files GraphicalAbstract.png Highlights.docx Cite Share Download PDF Status: Posted Version 1 posted 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-8755908","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":598632737,"identity":"e3873ef6-6e7a-4484-b6f4-56173ec2b2b0","order_by":0,"name":"Abtin Ijadi Maghsoodi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIiWNgGAWjYJACZjB5mPkwyVrYkknVcoDHmDjl/NMOP35d8MdGju84z2fjwpxaBv72BraHP/BokbidZmY9sy3NWPIw7+bkmduOM0icOcBuIIHPmtsJZsa8DYcTNwC1HObddozBQCKBTcIAjw752+nfjHn+gLTwPEZoScCjxeB2jvFjHjawFuZk3m01EC0H8GgxvJ1TxswL9gubsfHMbQd4JM4cbJNswKNF7nb65s88oBA7f/ixdOG2Ojn+9uZjkvhCDAjY4MEDjKDDPAwMjPjsgCj8gKSljpDqUTAKRsEoGIEAAEdbTD0/mSAqAAAAAElFTkSuQmCC","orcid":"","institution":"University of Waikato","correspondingAuthor":true,"prefix":"","firstName":"Abtin","middleName":"Ijadi","lastName":"Maghsoodi","suffix":""}],"badges":[],"createdAt":"2026-02-01 11:53:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8755908/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8755908/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106692651,"identity":"7ff6d61f-1a0b-441c-9450-3390ee3af0bc","added_by":"auto","created_at":"2026-04-11 21:39:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1074462,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptDraft.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8755908/v1_covered_6cb32c3d-1fd7-471c-b8a6-fc1937b6c527.pdf"},{"id":103824338,"identity":"78759b6b-a061-4052-88bd-730d3a538940","added_by":"auto","created_at":"2026-03-03 11:16:50","extension":"png","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":7367808,"visible":true,"origin":"","legend":"","description":"","filename":"GraphicalAbstract.png","url":"https://assets-eu.researchsquare.com/files/rs-8755908/v1/477bda0aea678004ae820848.png"},{"id":103824339,"identity":"cca754b8-ad88-4539-941b-bc398f9d13c4","added_by":"auto","created_at":"2026-03-03 11:16:51","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":233493,"visible":true,"origin":"","legend":"","description":"","filename":"Highlights.docx","url":"https://assets-eu.researchsquare.com/files/rs-8755908/v1/92b4037cd6b2ba5ea5adda5b.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"MOJO: Multi-LLM Optimised Joint Objective - Generative Artificial Intelligence for Multi-Criteria Decision Analysis Framework","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Multi-Criteria Decision Analysis (MCDA), Large Language Model (LLM), Artificial Intelligence, Generative AI (Gen-AI), Decision Bias","lastPublishedDoi":"10.21203/rs.3.rs-8755908/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8755908/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study introduces the Multi-LLM Optimised Joint Objective (MOJO), a novel generative artificial intelligence (Gen-AI) driven multi-criteria decision analysis (MCDA) framework. MOJO uniquely integrates human expertise with multiple large language models (LLMs) to address limitations in traditional MCDA approaches. The information fusion framework combines risk-adjusted utility scoring, performance equilibrium, and reliability scoring, producing consensus-driven rankings that effectively account for uncertainty and non-linear risk preferences. Grounded in principles from prospect theory and utility theory, MOJO captures complex behavioural factors such as loss aversion and probability distortion. An ensemble of LLM outputs automates MCDA tasks, enhanced by systematic bias correction to reduce cognitive load and improve transparency. MOJO also incorporates a comprehensive illustrative case study evaluating treatments for Inflammatory Bowel Disease (IBD), demonstrating its applicability to complex scenarios involving clinical, operational, and ethical criteria. Results from validation experiments involving multiple LLMs and decision-makers across diverse scenarios highlight MOJO's robustness, reliability, and transparency, demonstrating its significant potential in high-stakes fields such as healthcare, engineering, and public policy.\u003c/p\u003e","manuscriptTitle":"MOJO: Multi-LLM Optimised Joint Objective - Generative Artificial Intelligence for Multi-Criteria Decision Analysis Framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-03 11:16:45","doi":"10.21203/rs.3.rs-8755908/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"428812b7-1827-4c8d-8dfa-dfb40479dd73","owner":[],"postedDate":"March 3rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-11T21:38:46+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-03 11:16:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8755908","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8755908","identity":"rs-8755908","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}