Evaluating an LLM’s Performance in Annotating Discourse Strategies

Evaluating an LLM’s Performance in Annotating Discourse Strategies | 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 an LLM’s Performance in Annotating Discourse Strategies Taylor Meizlish, Chris Ziffo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7246876/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Jan, 2026 Read the published version in Corpus Pragmatics → Version 1 posted You are reading this latest preprint version Abstract Manual annotation remains essential for identifying complex pragmatic and discourse-level features in corpus linguistics, particularly the functional components of speech acts. While part-of-speech and semantic tagging can be automated with high accuracy, annotating discourse strategies remains challenging due to their context-sensitive nature and lack of consistent lexical realizations. These limitations hinder the scalability of function-to-form approaches and constrain the development of richly annotated corpora for pragmatics research and instruction. This study investigates whether a large language model (LLM), specifically ChatGPT-4, can support functional annotation of refusal strategies in English. A corpus of written Discourse Completion Tasks by Japanese university English learners was analyzed for reliability, human-rater agreement, accuracy, and generalizability. The results suggest an LLM can greatly assist the process of pragmatic annotation to increase scalability and accuracy. Corpus Pragmatics Speech Acts Discourse Strategies Refusal Strategies Large Language Models Speech Act Annotation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 07 Jan, 2026 Read the published version in Corpus Pragmatics → 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-7246876","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":506546980,"identity":"f909bc7f-6bbc-4f66-8580-f042491e4a21","order_by":0,"name":"Taylor Meizlish","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIiWNgGAWjYFACxgaGBwYMCfxA5geIyAEitCQAtUg2MDDOIFILECQAkcEBuBYCQLe9uflDQkFdnvHtHsPGHwx28gyMZ/FbY3bmYINBgsHhYrM7ZwybeRiSDRsYziXg13IjsSEB6KrEbTdyzB8zMDADlZ8xwK/l/sOGAwkGdYmbZ+SAHFZPhJYbjI0NCQbMiRskcgwbeBgOE6HlTGIzMLgOJ864kVbYzGNw3LCNoF+OH3/84cOfusT+GckbG39UVMvzSxAIMTQAdBKbxBlSdIABfw/JWkbBKBgFo2B4AwBaTU1QnqajUwAAAABJRU5ErkJggg==","orcid":"","institution":"Nagoya University of Foreign Studies","correspondingAuthor":true,"prefix":"","firstName":"Taylor","middleName":"","lastName":"Meizlish","suffix":""},{"id":506546981,"identity":"7c9a7c4c-1062-491d-8e3a-27184ea19eee","order_by":1,"name":"Chris Ziffo","email":"","orcid":"","institution":"Nagoya University of Foreign Studies","correspondingAuthor":false,"prefix":"","firstName":"Chris","middleName":"","lastName":"Ziffo","suffix":""}],"badges":[],"createdAt":"2025-07-29 22:23:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7246876/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7246876/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s41701-025-00224-2","type":"published","date":"2026-01-07T15:58:16+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100069940,"identity":"8375dad8-88e9-4fd7-9d3c-c153a1c16529","added_by":"auto","created_at":"2026-01-12 16:15:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":829384,"visible":true,"origin":"","legend":"","description":"","filename":"EvaluatinganLLMsPerformanceinAnnotatingDiscourseStrategies.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7246876/v1_covered_5e1d1807-a5f0-4774-997c-d651ed8f9f34.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Evaluating an LLM’s Performance in Annotating Discourse Strategies","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"Corpus Pragmatics, Speech Acts, Discourse Strategies, Refusal Strategies, Large Language Models, Speech Act Annotation","lastPublishedDoi":"10.21203/rs.3.rs-7246876/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7246876/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eManual annotation remains essential for identifying complex pragmatic and discourse-level features in corpus linguistics, particularly the functional components of speech acts. While part-of-speech and semantic tagging can be automated with high accuracy, annotating discourse strategies remains challenging due to their context-sensitive nature and lack of consistent lexical realizations. These limitations hinder the scalability of function-to-form approaches and constrain the development of richly annotated corpora for pragmatics research and instruction. This study investigates whether a large language model (LLM), specifically ChatGPT-4, can support functional annotation of refusal strategies in English. A corpus of written Discourse Completion Tasks by Japanese university English learners was analyzed for reliability, human-rater agreement, accuracy, and generalizability. The results suggest an LLM can greatly assist the process of pragmatic annotation to increase scalability and accuracy.\u003c/p\u003e","manuscriptTitle":"Evaluating an LLM’s Performance in Annotating Discourse Strategies","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-02 08:11:26","doi":"10.21203/rs.3.rs-7246876/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":"967cf517-ed7a-4017-af0e-ae5975a6a903","owner":[],"postedDate":"September 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-12T16:08:40+00:00","versionOfRecord":{"articleIdentity":"rs-7246876","link":"https://doi.org/10.1007/s41701-025-00224-2","journal":{"identity":"corpus-pragmatics","isVorOnly":false,"title":"Corpus Pragmatics"},"publishedOn":"2026-01-07 15:58:16","publishedOnDateReadable":"January 7th, 2026"},"versionCreatedAt":"2025-09-02 08:11:26","video":"","vorDoi":"10.1007/s41701-025-00224-2","vorDoiUrl":"https://doi.org/10.1007/s41701-025-00224-2","workflowStages":[]},"version":"v1","identity":"rs-7246876","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7246876","identity":"rs-7246876","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}