ChatBCI: A P300 Speller BCI Leveraging Large Language Models for Improved Sentence Composition in Realistic Scenarios

ChatBCI: A P300 Speller BCI Leveraging Large Language Models for Improved Sentence Composition in Realistic Scenarios | 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 Article ChatBCI: A P300 Speller BCI Leveraging Large Language Models for Improved Sentence Composition in Realistic Scenarios Jiazhen Hong, Weinan Wang, Laleh Najafizadeh This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6550319/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Feb, 2026 Read the published version in Scientific Reports → Version 1 posted 29 You are reading this latest preprint version Abstract P300 speller brain computer interfaces (BCIs) allow users to compose sentences by selecting target keys on a graphical user interface (GUI) through the detection of P300 component in their electroencephalogram (EEG) signals following visual stimuli. Most existing P300 speller BCIs require users to spell all or the first few initial letters of the intended word, letter by letter. Consequently, a large number of keystrokes could be required to write an intended sentence, thereby, increasing user’s time and cognitive load. There is a need for more efficient and user-friendly methods for faster, and practical sentence composition. In this work, we introduce ChatBCI, a P300 speller BCI that leverages the zero-shot learning capabilities of large language models (LLMs) to suggest words from user-spelled initial letters or predict the subsequent word(s), reducing keystrokes and accelerating sentence composition. ChatBCI retrieves word suggestions through remote queries to the GPT-3.5 API. A modified GUI, displaying GPT-3.5 word suggestions as extra keys is designed. Stepwise linear discriminant analysis (SWLDA) is used for the P300 classification. Seven subjects completed two online spelling tasks: 1) copy-spelling a self-composed sentence using ChatBCI, and 2) improvising a sentence using ChatBCI’s word suggestions. Results demonstrate that for the copy-spelling task, on average, ChatBCI outperforms letter-by-letter BCI spellers, reducing time and keystrokes by 62.14% and 53.22%, respectively, and increasing information transfer rate by 229.48%. For the improvised sessions, ChatBCI achieves 80.68% keystroke savings across subjects. Overall, ChatBCI, by employing remote LLM queries outperforms traditional spellers without requiring local model training or storage. ChatBCI’s (multi-) word predictions-capability paves the way for developing next-generation speller BCIs that are efficient and effective for real-time communication, specially for users with communication and motor disabilities. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Engineering/Biomedical engineering Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Feb, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 17 Jun, 2025 Reviews received at journal 04 Jun, 2025 Reviews received at journal 01 Jun, 2025 Reviews received at journal 01 Jun, 2025 Reviews received at journal 30 May, 2025 Reviews received at journal 28 May, 2025 Reviews received at journal 23 May, 2025 Reviews received at journal 23 May, 2025 Reviews received at journal 22 May, 2025 Reviews received at journal 21 May, 2025 Reviews received at journal 20 May, 2025 Reviewers agreed at journal 15 May, 2025 Reviewers agreed at journal 14 May, 2025 Reviews received at journal 13 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers invited by journal 13 May, 2025 Editor assigned by journal 13 May, 2025 Editor invited by journal 09 May, 2025 Submission checks completed at journal 09 May, 2025 First submitted to journal 28 Apr, 2025 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-6550319","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":456740562,"identity":"65528eeb-d2d0-429c-9ac4-7a692ae5f51e","order_by":0,"name":"Jiazhen Hong","email":"","orcid":"","institution":"Rutgers, The State University of New Jersey","correspondingAuthor":false,"prefix":"","firstName":"Jiazhen","middleName":"","lastName":"Hong","suffix":""},{"id":456740563,"identity":"84dabcca-37c1-45bf-a29c-15eff85ec4e9","order_by":1,"name":"Weinan Wang","email":"","orcid":"","institution":"Rutgers, The State University of New Jersey","correspondingAuthor":false,"prefix":"","firstName":"Weinan","middleName":"","lastName":"Wang","suffix":""},{"id":456740564,"identity":"56c84e73-a29a-4ad3-b37c-373c6401e427","order_by":2,"name":"Laleh Najafizadeh","email":"data:image/png;base64,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","orcid":"","institution":"Rutgers, The State University of New Jersey","correspondingAuthor":true,"prefix":"","firstName":"Laleh","middleName":"","lastName":"Najafizadeh","suffix":""}],"badges":[],"createdAt":"2025-04-28 18:53:03","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6550319/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6550319/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-25660-7","type":"published","date":"2026-02-16T15:58:19+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":103251925,"identity":"76481a25-e1b0-4cae-b670-02bc8413b433","added_by":"auto","created_at":"2026-02-23 16:12:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3291497,"visible":true,"origin":"","legend":"","description":"","filename":"Submission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6550319/v1_covered_f80f1c4f-06a9-49e0-af2d-d5692ad023ce.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"ChatBCI: A P300 Speller BCI Leveraging Large Language Models for Improved Sentence Composition in Realistic Scenarios","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6550319/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6550319/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"P300 speller brain computer interfaces (BCIs) allow users to compose sentences by selecting target keys on a graphical user interface (GUI) through the detection of P300 component in their electroencephalogram (EEG) signals following visual stimuli. Most existing P300 speller BCIs require users to spell all or the first few initial letters of the intended word, letter by letter. Consequently, a large number of keystrokes could be required to write an intended sentence, thereby, increasing user’s time and cognitive load. There is a need for more efficient and user-friendly methods for faster, and practical sentence composition.\n\nIn this work, we introduce ChatBCI, a P300 speller BCI that leverages the zero-shot learning capabilities of large language models (LLMs) to suggest words from user-spelled initial letters or predict the subsequent word(s), reducing keystrokes and accelerating sentence composition. ChatBCI retrieves word suggestions through remote queries to the GPT-3.5 API. A modified GUI, displaying GPT-3.5 word suggestions as extra keys is designed. Stepwise linear discriminant analysis (SWLDA) is used for the P300 classification. Seven subjects completed two online spelling tasks: 1) copy-spelling a self-composed sentence using ChatBCI, and 2) improvising a sentence using ChatBCI’s word suggestions. Results demonstrate that for the copy-spelling task, on average, ChatBCI outperforms letter-by-letter BCI spellers, reducing time and keystrokes by 62.14% and 53.22%, respectively, and increasing information transfer rate by 229.48%. For the improvised sessions, ChatBCI achieves 80.68% keystroke savings across subjects. Overall, ChatBCI, by employing remote LLM queries outperforms traditional spellers without requiring local model training or storage. ChatBCI’s (multi-) word predictions-capability paves the way for developing next-generation speller BCIs that are efficient and effective for real-time communication, specially for users with communication and motor disabilities.","manuscriptTitle":"ChatBCI: A P300 Speller BCI Leveraging Large Language Models for Improved Sentence Composition in Realistic Scenarios","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-15 06:04:10","doi":"10.21203/rs.3.rs-6550319/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-17T04:52:17+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-04T11:25:07+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-01T19:21:04+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-01T15:51:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-30T21:05:43+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-28T11:56:18+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-23T12:07:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-23T08:19:03+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-22T14:43:06+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-22T02:36:04+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-20T15:55:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"218396649944080342262886164887471673810","date":"2025-05-15T07:09:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"72428930659525265636895851025313236317","date":"2025-05-14T21:08:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-13T16:40:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"269881241043108209041777642114753880652","date":"2025-05-13T16:34:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"231084734518095784019720051789939228185","date":"2025-05-13T15:57:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"181794938927178033275157636479215580445","date":"2025-05-13T11:44:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"159638555745028135444264690213759835009","date":"2025-05-13T11:12:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"255644110874173526297593425699460402549","date":"2025-05-13T09:09:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"325625343179126656799668546286515238824","date":"2025-05-13T08:57:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"195660371338672075305466728121154770662","date":"2025-05-13T08:54:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"79435246186931165557301541928571112094","date":"2025-05-13T08:22:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"147800574545878418003849599712402794660","date":"2025-05-13T07:53:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"27514155448217155813585763198584798366","date":"2025-05-13T07:52:55+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-13T07:23:29+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-13T07:19:40+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-09T12:55:37+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-09T07:55:13+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-04-28T18:37:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"21b336e2-bc52-427c-962e-6adeb46b5521","owner":[],"postedDate":"May 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":48546231,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":48546232,"name":"Physical sciences/Engineering/Biomedical engineering"}],"tags":[],"updatedAt":"2026-02-23T16:08:56+00:00","versionOfRecord":{"articleIdentity":"rs-6550319","link":"https://doi.org/10.1038/s41598-025-25660-7","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-02-16 15:58:19","publishedOnDateReadable":"February 16th, 2026"},"versionCreatedAt":"2025-05-15 06:04:10","video":"","vorDoi":"10.1038/s41598-025-25660-7","vorDoiUrl":"https://doi.org/10.1038/s41598-025-25660-7","workflowStages":[]},"version":"v1","identity":"rs-6550319","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6550319","identity":"rs-6550319","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}