Research on Improving Ethical Sensitivity for Ethical Decision-Making in Conversational AI

Research on Improving Ethical Sensitivity for Ethical Decision-Making in Conversational AI | 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 Research on Improving Ethical Sensitivity for Ethical Decision-Making in Conversational AI Kyungsun Yoo, Seongjin Ahn This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4999457/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Mar, 2025 Read the published version in Discover Computing → Version 1 posted 14 You are reading this latest preprint version Abstract The development of large language models has significantly advanced the inferential capabilities of artificial intelligence (AI), surpassing human-level performance. Despite the rapid growth in AI's cognitive abilities and the consequent expectations for high-level ethical judgments, ethical issues have increased. This indicates a heightened risk of bias as AI models scale up and train on vast amounts of general data that inherently include social conventions related to gender, race, politics, and religion. This study proposes methods for enhancing ethical sensitivity to social bias. To achieve this, we defined 20 categories of social bias and developed a model that predicts the ethical sensitivity of sentences by leveraging the influence scores of words within these categories. The ethical sensitivity prediction model was validated using a paired-sample t-test, comparing the ethical sensitivity evaluations of 25 AI-generated responses assessed by both AI and human evaluators. The test revealed no significant differences between the two groups, thus confirming the validity of the model. The findings of this study suggest that recognizing and predicting the ethical sensitivity of utterances concerning social biases can enhance ethical sensitivity, mitigate the risk of bias, and contribute to more ethical decision-making in AI interactions. Ethics of artificial intelligence conversational artificial intelligence large language model ethical judgment ethical sensitivity Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 25 Mar, 2025 Read the published version in Discover Computing → Version 1 posted Editorial decision: Revision requested 05 Nov, 2024 Reviews received at journal 18 Oct, 2024 Reviews received at journal 17 Oct, 2024 Reviews received at journal 17 Oct, 2024 Reviewers agreed at journal 11 Oct, 2024 Reviewers agreed at journal 11 Oct, 2024 Reviewers agreed at journal 11 Oct, 2024 Reviews received at journal 19 Sep, 2024 Reviewers agreed at journal 16 Sep, 2024 Reviewers agreed at journal 15 Sep, 2024 Reviewers invited by journal 11 Sep, 2024 Editor assigned by journal 10 Sep, 2024 Submission checks completed at journal 05 Sep, 2024 First submitted to journal 29 Aug, 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-4999457","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":358829886,"identity":"5e8eab38-3fc5-4785-974a-c26a5e0e1d1e","order_by":0,"name":"Kyungsun Yoo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6UlEQVRIie3OsarCMBSA4RQhWVLniNi+QkpAHMRnSSh0inJBkDsWhDi66uI7uIhjIKBLBseOOrk41K2b17q4hbpdMN9yOHB+OAB43j8WQZQ/h+b1QhslrI31h4nYEN4wiVdjU973QwY711NQ2UzkaL4jroQWE56sbRbBrvxp4UKKHB9m7oRImobKsGfCW6D8FTmRfWcSryQ1oXoI1bE8qOokvrkTUMhkHiotFEEavB4j2J1Qe2PBWqUMYgkMthlTOJsOnI8tJCvvahTFi+PlUh3S3hKZbeF87A1TXQ/Y8LyGzh8ce57nfZM/8nBKLiTvvhcAAAAASUVORK5CYII=","orcid":"","institution":"Sungkyunkwan University","correspondingAuthor":true,"prefix":"","firstName":"Kyungsun","middleName":"","lastName":"Yoo","suffix":""},{"id":358829887,"identity":"ed14da62-cb4f-4837-adf9-bdb2fc41bb4c","order_by":1,"name":"Seongjin Ahn","email":"","orcid":"","institution":"Sungkyunkwan University","correspondingAuthor":false,"prefix":"","firstName":"Seongjin","middleName":"","lastName":"Ahn","suffix":""}],"badges":[],"createdAt":"2024-08-29 18:00:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4999457/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4999457/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10791-025-09520-6","type":"published","date":"2025-03-25T15:57:46+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":79605656,"identity":"f0277e1d-a889-4c72-9b5e-f46e696df439","added_by":"auto","created_at":"2025-03-31 16:11:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":594617,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4999457/v1_covered_bb65f961-e4d5-4b73-a4f6-716bb6e59069.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Research on Improving Ethical Sensitivity for Ethical Decision-Making in Conversational AI","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":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Ethics of artificial intelligence, conversational artificial intelligence, large language model, ethical judgment, ethical sensitivity","lastPublishedDoi":"10.21203/rs.3.rs-4999457/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4999457/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe development of large language models has significantly advanced the inferential capabilities of artificial intelligence (AI), surpassing human-level performance. Despite the rapid growth in AI's cognitive abilities and the consequent expectations for high-level ethical judgments, ethical issues have increased. This indicates a heightened risk of bias as AI models scale up and train on vast amounts of general data that inherently include social conventions related to gender, race, politics, and religion. This study proposes methods for enhancing ethical sensitivity to social bias. To achieve this, we defined 20 categories of social bias and developed a model that predicts the ethical sensitivity of sentences by leveraging the influence scores of words within these categories. The ethical sensitivity prediction model was validated using a paired-sample t-test, comparing the ethical sensitivity evaluations of 25 AI-generated responses assessed by both AI and human evaluators. The test revealed no significant differences between the two groups, thus confirming the validity of the model. The findings of this study suggest that recognizing and predicting the ethical sensitivity of utterances concerning social biases can enhance ethical sensitivity, mitigate the risk of bias, and contribute to more ethical decision-making in AI interactions.\u003c/p\u003e","manuscriptTitle":"Research on Improving Ethical Sensitivity for Ethical Decision-Making in Conversational AI","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-07 15:05:43","doi":"10.21203/rs.3.rs-4999457/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-11-05T05:27:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-18T07:17:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-17T13:48:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-17T06:01:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"91104998578691497727606836556858601442","date":"2024-10-11T11:29:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"70202440096442226180937879058115786322","date":"2024-10-11T10:38:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"84724692469119084392914892967190426811","date":"2024-10-11T10:19:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-19T10:34:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"152977027061243294986411726823075840993","date":"2024-09-16T17:22:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"271699147339989045472342395507707226304","date":"2024-09-15T12:10:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-09-11T17:09:18+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-09-10T12:55:32+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-09-05T04:21:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Computing","date":"2024-08-29T17:58:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"eae6451e-d3ab-4a73-aa2c-5edf5a2b169d","owner":[],"postedDate":"October 7th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-03-31T16:08:46+00:00","versionOfRecord":{"articleIdentity":"rs-4999457","link":"https://doi.org/10.1007/s10791-025-09520-6","journal":{"identity":"discover-computing","isVorOnly":false,"title":"Discover Computing"},"publishedOn":"2025-03-25 15:57:46","publishedOnDateReadable":"March 25th, 2025"},"versionCreatedAt":"2024-10-07 15:05:43","video":"","vorDoi":"10.1007/s10791-025-09520-6","vorDoiUrl":"https://doi.org/10.1007/s10791-025-09520-6","workflowStages":[]},"version":"v1","identity":"rs-4999457","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4999457","identity":"rs-4999457","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}