{"paper_id":"1164ce01-1bcf-4756-9fce-a453bc4ea2bb","body_text":"Exploring LLM-generated Culture-specific Affective Human-Robot Tactile Interaction | 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 Exploring LLM-generated Culture-specific Affective Human-Robot Tactile Interaction Qiaoqiao ren, Tony Belpaeme This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7072993/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 As large language models (LLMs) become increasingly integrated into robotic systems, their potential to generate socially and culturally appropriate affective touch remains largely unexplored. This study investigates whether LLMs-specifically GPT-3.5, GPT-4, and GPT-4o --can generate culturally adaptive tactile behaviours to convey emotions in human-robot interaction. We produced text based touch descriptions for 12 distinct emotions across three cultural contexts (Chinese, Belgian, and unspecified), and examined their interpretability in both robot-to-human and human-to-robot scenarios. A total of 90 participants (36 Chinese, 36 Belgian, and 18 culturally unspecified) evaluated these LLM-generated tactile behaviours for emotional decoding and perceived appropriateness. Results reveal that: (1) under matched cultural conditions, participants successfully decoded six out of twelve emotions-mainly socially oriented emotions such as love and Ekman emotions such as anger, however, self-focused emotions like pride and embarrassment were more difficult to interpret; (2) tactile behaviours were perceived as more appropriate when directed from human to robot than from robot to human, revealing an asymmetry in social expectations based on interaction roles; (3) behaviours interpreted as aggressive (e.g., anger), overly intimate (e.g., love), or emotionally ambiguous (i.e., not clearly decodable) were significantly more likely to be rated as inappropriate; and (4) cultural mismatches reduced decoding accuracy and increased the likelihood of behaviours being judged as inappropriate. Robotics Tactile interaction affective computing emotion decoding cultural difference Full Text Additional Declarations The authors declare no competing interests. Ghent University upholds strict ethic guidelines and subscribes to the General Data Protection Regulation (GDPR). The research reported in the manuscript has received ethical approval from the Faculty of Engineering and Architecture at Ghent University based on a self-assessment of the research risks. The study was conducted in accordance with the Declaration of Helsinki and the European Code of Conduct for Research Integrity, and was conducted in accordance with the regulations and code of conduct of the Faculty of Engineering and Architecture, Ghent University (Ethische Code van het Wetenschappelijk Onderzoek in België, D/2009/1191/6). 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-7072993\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":482267878,\"identity\":\"10957e07-ac61-41b9-9786-cfeb7690188c\",\"order_by\":0,\"name\":\"Qiaoqiao ren\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYDACZhBhAOV8gFBsxGthnAHRQEALinYeYrTwHWd++OBNgZ0cg/ThY49t22rlzOUb2B58wKNF8jCbseEcg2RjBr60dOPctuPGlm0M7IYz8GgxOMxgJs1jwJzYwMNjJp3bdixxwzEGNmkevFrYvwG11AO18H+Ttmw7Vg/W8gevFh6QLYdBtrBJM7bVJBiAtODzvuRhnmKgX44bs/GwmUn2nDtguOFYYrthDx4tfOePb3zw5k+1HD8P8zOJH2V18gaHDx978AOfNQeAGORZaFwcBmLGBnwaEFqgoA6/6lEwCkbBKBiRAAAFT0O4orcEFwAAAABJRU5ErkJggg==\",\"orcid\":\"\",\"institution\":\"Ghent University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Qiaoqiao\",\"middleName\":\"\",\"lastName\":\"ren\",\"suffix\":\"\"},{\"id\":482267879,\"identity\":\"90e523de-922c-44c5-9dbf-a8a6bd36c2f4\",\"order_by\":1,\"name\":\"Tony Belpaeme\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Ghent University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Tony\",\"middleName\":\"\",\"lastName\":\"Belpaeme\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-07-08 09:13:54\",\"currentVersionCode\":1,\"declarations\":{\"humanSubjects\":true,\"vertebrateSubjects\":false,\"conflictsOfInterestStatement\":false,\"humanSubjectEthicalGuidelines\":true,\"humanSubjectConsent\":true,\"humanSubjectClinicalTrial\":false,\"humanSubjectCaseReport\":false,\"vertebrateSubjectEthicalGuidelines\":false},\"doi\":\"10.21203/rs.3.rs-7072993/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-7072993/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":86380414,\"identity\":\"8933cd72-779b-44ae-89b9-b6c3ed9092e9\",\"added_by\":\"auto\",\"created_at\":\"2025-07-10 04:07:42\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":388978,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"ICSR2025.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7072993/v1_covered_f6810a66-2b62-4649-80e4-a449aba8964a.pdf\"}],\"financialInterests\":\"\\u003cp\\u003eThe authors declare no competing interests.\\u003c/p\\u003e\\n\\u003cp\\u003eGhent University upholds strict ethic guidelines and subscribes to the General Data Protection Regulation (GDPR). The research reported in the manuscript has received ethical approval from the Faculty of Engineering and Architecture at Ghent University based on a self-assessment of the research risks.\\u003c/p\\u003e\\n\\u003cp\\u003eThe study was conducted in accordance with the Declaration of Helsinki and the European Code of Conduct for Research Integrity, and was conducted in accordance with the regulations and code of conduct of the Faculty of Engineering and Architecture, Ghent University (Ethische Code van het Wetenschappelijk Onderzoek in België, D/2009/1191/6).\\u003c/p\\u003e\",\"formattedTitle\":\"\\u003cp\\u003eExploring LLM-generated Culture-specific Affective Human-Robot Tactile Interaction\\u003c/p\\u003e\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":true,\"hideJournal\":true,\"highlight\":\"\",\"institution\":\"Ghent University\",\"isAcceptedByJournal\":false,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"Tactile interaction, affective computing, emotion decoding, cultural difference\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-7072993/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-7072993/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eAs large language models (LLMs) become increasingly integrated into robotic systems, their potential to generate socially and culturally appropriate affective touch remains largely unexplored. This study investigates whether LLMs-specifically GPT-3.5, GPT-4, and GPT-4o --can generate culturally adaptive tactile behaviours to convey emotions in human-robot interaction. We produced text based touch descriptions for 12 distinct emotions across three cultural contexts (Chinese, Belgian, and unspecified), and examined their interpretability in both robot-to-human and human-to-robot scenarios. A total of 90 participants (36 Chinese, 36 Belgian, and 18 culturally unspecified) evaluated these LLM-generated tactile behaviours for emotional decoding and perceived appropriateness. Results reveal that: (1) under matched cultural conditions, participants successfully decoded six out of twelve emotions-mainly socially oriented emotions such as love and Ekman emotions such as anger, however, self-focused emotions like pride and embarrassment were more difficult to interpret; (2) tactile behaviours were perceived as more appropriate when directed from human to robot than from robot to human, revealing an asymmetry in social expectations based on interaction roles; (3) behaviours interpreted as aggressive (e.g., anger), overly intimate (e.g., love), or emotionally ambiguous (i.e., not clearly decodable) were significantly more likely to be rated as inappropriate; and (4) cultural mismatches reduced decoding accuracy and increased the likelihood of behaviours being judged as inappropriate.\\u003c/p\\u003e\",\"manuscriptTitle\":\"Exploring LLM-generated Culture-specific Affective Human-Robot Tactile Interaction\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-07-10 03:59:35\",\"doi\":\"10.21203/rs.3.rs-7072993/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"b64007a5-7820-48f2-8503-55df13b4bbb5\",\"owner\":[],\"postedDate\":\"July 10th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[{\"id\":51205580,\"name\":\"Robotics\"}],\"tags\":[],\"updatedAt\":\"2025-07-10T03:59:35+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2025-07-10 03:59:35\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-7072993\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-7072993\",\"identity\":\"rs-7072993\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}