Evaluating Multimodal Large Language Models for Implicit Advertising Reasoning

Evaluating Multimodal Large Language Models for Implicit Advertising Reasoning | 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 Evaluating Multimodal Large Language Models for Implicit Advertising Reasoning Haozhi Sun, Heng Yuan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5914045/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 In this paper, we present a novel method for implicit reasoning in advertising, focusing on the use of a multimodal large language model integrated with a specialized prompt engineering approach. Advertising often involves implicit reasoning, where messages are conveyed indirectly through a combination of text, images, and emotions. This makes it challenging for traditional models to capture the subtle nuances involved. To address this, we propose an innovative multi-round prompt design that enables the model to refine its reasoning process iteratively, thus improving its ability to decode implicit intentions in advertisements. Our method leverages GPT-4 as the core reasoning engine, and the prompts are designed to guide the model through multiple reasoning phases, ensuring that it effectively incorporates both textual and visual cues. We collect a custom dataset of advertising content to train and evaluate our approach, and our results demonstrate significant improvements in reasoning accuracy compared to baseline models. We also propose novel evaluation metrics, which go beyond traditional accuracy and incorporate human-like reasoning assessments. Experimental results and human evaluations show that our method outperforms existing models, both in terms of reasoning depth and interpretability, making it a promising solution for understanding complex advertising content. Implicit Advertising Reasoning Multimodal Large Language Model Full Text Additional Declarations The authors declare no competing interests. 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-5914045","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":407810669,"identity":"43cfa3fa-0a59-4b79-8b6c-7430aab1140e","order_by":0,"name":"Haozhi Sun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCklEQVRIie3QMUvDQBTA8RcOrsuDrBcq6kd4cFAqKe1XyRHQTQQXx6SBuNk1gx/Cj3DhwC5C14Muze6QyamgZycdLmQUvP8UjvxyLw8gFPqDxSwqDxktMP55KoZI8lhV1N9dnyUFG0nobVsnTW8WpMcSsKqeIjGUu92rgGOqXjRr9wjLW5+IGlWlSBxnNuciqm8kaZ6nCPm9jzChyj0SOsIcKcw5aZxNEbQqPIQLVbjBBMqN4W4wg6Tjj0GC2K6ThggJ3GDAT7fwQSImpVsyZShsLufK/UtiuLx6ptxLVmbSHbLj5yretJ3t3caetlVn3x+WXvK7DBhcmu8nGvX+KQYX474eCoVC/6gvwRNSFRrc0owAAAAASUVORK5CYII=","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":true,"prefix":"","firstName":"Haozhi","middleName":"","lastName":"Sun","suffix":""},{"id":407810670,"identity":"3a81a6ae-a1c3-4b68-98fa-bdaf0faf5c16","order_by":1,"name":"Heng Yuan","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Heng","middleName":"","lastName":"Yuan","suffix":""}],"badges":[],"createdAt":"2025-01-27 17:09:16","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-5914045/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5914045/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":74981285,"identity":"d6750716-7cec-42d7-b103-b6b1422a2c0c","added_by":"auto","created_at":"2025-01-29 04:50:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":107863,"visible":true,"origin":"","legend":"","description":"","filename":"Advertising.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5914045/v1_covered_ecf8a708-1d3f-4fa8-9db1-bca3cfa50297.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eEvaluating Multimodal Large Language Models for Implicit Advertising Reasoning\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Henan Polytechnic University","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":"Implicit Advertising Reasoning, Multimodal Large Language Model","lastPublishedDoi":"10.21203/rs.3.rs-5914045/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5914045/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn this paper, we present a novel method for implicit reasoning in advertising, focusing on the use of a multimodal large language model integrated with a specialized prompt engineering approach. Advertising often involves implicit reasoning, where messages are conveyed indirectly through a combination of text, images, and emotions. This makes it challenging for traditional models to capture the subtle nuances involved. To address this, we propose an innovative multi-round prompt design that enables the model to refine its reasoning process iteratively, thus improving its ability to decode implicit intentions in advertisements. Our method leverages GPT-4 as the core reasoning engine, and the prompts are designed to guide the model through multiple reasoning phases, ensuring that it effectively incorporates both textual and visual cues. We collect a custom dataset of advertising content to train and evaluate our approach, and our results demonstrate significant improvements in reasoning accuracy compared to baseline models. We also propose novel evaluation metrics, which go beyond traditional accuracy and incorporate human-like reasoning assessments. Experimental results and human evaluations show that our method outperforms existing models, both in terms of reasoning depth and interpretability, making it a promising solution for understanding complex advertising content.\u003c/p\u003e","manuscriptTitle":"Evaluating Multimodal Large Language Models for Implicit Advertising Reasoning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-29 04:42:10","doi":"10.21203/rs.3.rs-5914045/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":"414b461a-23ae-45f2-a452-05e3473a58ae","owner":[],"postedDate":"January 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-01-29T04:42:10+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-29 04:42:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5914045","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5914045","identity":"rs-5914045","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}