PipeMoE-NER: MoE-LoRA Expert Adaptation and Three-Stage Chain-of-Thought for Pipeline Safety NER

PipeMoE-NER: MoE-LoRA Expert Adaptation and Three-Stage Chain-of-Thought for Pipeline Safety NER | 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 PipeMoE-NER: MoE-LoRA Expert Adaptation and Three-Stage Chain-of-Thought for Pipeline Safety NER Jiannan Zhai, Xiang Mao, Guangyue Zhou, Qiutong Zheng, Xuankai Liao, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9148456/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Accurately identifying key entities such as units, risks, consequences, and measures within unstructured texts—including incident reports, inspection records, and management documents—in enterprise pipeline safety scenarios is a critical foundation for risk assessment and emergency decision-making. However, texts in this domain often suffer from dense terminology, drifting semantic boundaries of entities, and long-tailed category distributions. These issues lead to insufficient recall in traditional sequence labeling models and unstable structured outputs or boundary overruns when using end-to-end extraction with large models. To address these challenges, this paper proposes PipeMoE-NER, a specialized adaptation method based on MoE-LoRA and a three-stage Chain-of-Thought (CoT) reasoning approach for Named Entity Recognition (NER) in pipeline safety. On the modeling side, we employ a parameter-efficient expert adaptation strategy that combines the Mixture of Experts (MoE) architecture with the LoRA technique to enhance the modeling capability for long-tail patterns and professional expressions. On the inference side, we design a three-stage Chain-of-Thought prompting process. This process decomposes the extraction task into "candidate generation," "individual discrimination and typing," and "review, verification, and structured output," while introducing explicit constraints to improve type discrimination consistency and JSON output compliance.We constructed and annotated a private Chinese pipeline safety dataset containing five entity types: UNT, RSK, OUT, PRE, and MIT. We evaluated the model using strict entity-level metrics. Experimental results show that PipeMoE-NER achieves an overall F1-score of 81.50 and a Macro-F1 of 80.54 on the test set. This performance surpasses both ChatGLM3-6B Direct (78.49 F1) and DeBERTa-v3+CRF (66.12 F1), validating the effectiveness and robustness of the proposed method for entity recognition tasks in this domain. Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 30 Apr, 2026 Reviews received at journal 17 Apr, 2026 Reviewers agreed at journal 12 Apr, 2026 Reviews received at journal 10 Apr, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers invited by journal 08 Apr, 2026 Editor invited by journal 06 Apr, 2026 Editor assigned by journal 20 Mar, 2026 Submission checks completed at journal 20 Mar, 2026 First submitted to journal 17 Mar, 2026 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-9148456","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":621690495,"identity":"6ef00507-b60a-4929-8051-d6fdccfedced","order_by":0,"name":"Jiannan Zhai","email":"","orcid":"","institution":"PipeChina Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jiannan","middleName":"","lastName":"Zhai","suffix":""},{"id":621690496,"identity":"8a901c85-1cb8-44f6-b1ae-8ada60bc05a0","order_by":1,"name":"Xiang Mao","email":"","orcid":"","institution":"China University of Petroleum (East China)","correspondingAuthor":false,"prefix":"","firstName":"Xiang","middleName":"","lastName":"Mao","suffix":""},{"id":621690497,"identity":"95fec4f0-6db8-4b20-a3c7-d1e171859379","order_by":2,"name":"Guangyue Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9ElEQVRIie3QPYrCQBTA8RcCSfOi7QsL8QojAUVY9CoJgVQpttxyqqTRI3gIu5QzBLSZA2w5srA26wEEi52N7IKIiaXF/KthmN98AdhsTxjzK9GcGaHn87+5pIegSjW+v0YDFI8SSmLD8jii/5U9ZApJTmHZpGV40G5Qz2HoFwxO9X0y43JL41/yUjA3UBmEy2/mrFTHxSTPKb0QcINSAPsw1ik7SAMTku3Fdroli16yhXjMzfM9AnY5hXrIbInpJ5hP9rBgcq0yJPX1JlcdZDo6iMbsjKNqt9fHeh4Nq2yjTx3kKuFwwHbwIDAZYrPZbLabfgDK+VA6XWQkFwAAAABJRU5ErkJggg==","orcid":"","institution":"China University of Petroleum (East China)","correspondingAuthor":true,"prefix":"","firstName":"Guangyue","middleName":"","lastName":"Zhou","suffix":""},{"id":621690498,"identity":"fa8592cc-46e1-455b-907f-254e0da7e791","order_by":3,"name":"Qiutong Zheng","email":"","orcid":"","institution":"China University of Petroleum (East China)","correspondingAuthor":false,"prefix":"","firstName":"Qiutong","middleName":"","lastName":"Zheng","suffix":""},{"id":621690499,"identity":"3ccadaf5-9d25-4e8d-9d32-128511b9f1a1","order_by":4,"name":"Xuankai Liao","email":"","orcid":"","institution":"China University of Petroleum (East China)","correspondingAuthor":false,"prefix":"","firstName":"Xuankai","middleName":"","lastName":"Liao","suffix":""},{"id":621690500,"identity":"aec220d8-a4fb-4296-95a8-cca4c86065fc","order_by":5,"name":"Kewen Li","email":"","orcid":"","institution":"China University of Petroleum (East China)","correspondingAuthor":false,"prefix":"","firstName":"Kewen","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2026-03-17 11:53:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9148456/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9148456/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107480905,"identity":"ba20c72d-330a-4ae1-aa8c-2cc0537ee1d3","added_by":"auto","created_at":"2026-04-22 02:14:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":871325,"visible":true,"origin":"","legend":"","description":"","filename":"papersrep.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9148456/v1_covered_e9a14623-1305-48a1-836f-e6024c6f5f0f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"PipeMoE-NER: MoE-LoRA Expert Adaptation and Three-Stage Chain-of-Thought for Pipeline Safety NER","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"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-9148456/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9148456/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurately identifying key entities such as units, risks, consequences, and measures within unstructured texts—including incident reports, inspection records, and management documents—in enterprise pipeline safety scenarios is a critical foundation for risk assessment and emergency decision-making. However, texts in this domain often suffer from dense terminology, drifting semantic boundaries of entities, and long-tailed category distributions. These issues lead to insufficient recall in traditional sequence labeling models and unstable structured outputs or boundary overruns when using end-to-end extraction with large models. To address these challenges, this paper proposes PipeMoE-NER, a specialized adaptation method based on MoE-LoRA and a three-stage Chain-of-Thought (CoT) reasoning approach for Named Entity Recognition (NER) in pipeline safety.\u003c/p\u003e\n\u003cp\u003eOn the modeling side, we employ a parameter-efficient expert adaptation strategy that combines the Mixture of Experts (MoE) architecture with the LoRA technique to enhance the modeling capability for long-tail patterns and professional expressions. On the inference side, we design a three-stage Chain-of-Thought prompting process. This process decomposes the extraction task into \"candidate generation,\" \"individual discrimination and typing,\" and \"review, verification, and structured output,\" while introducing explicit constraints to improve type discrimination consistency and JSON output compliance.We constructed and annotated a private Chinese pipeline safety dataset containing five entity types: UNT, RSK, OUT, PRE, and MIT. We evaluated the model using strict entity-level metrics. Experimental results show that PipeMoE-NER achieves an overall F1-score of 81.50 and a Macro-F1 of 80.54 on the test set. This performance surpasses both ChatGLM3-6B Direct (78.49 F1) and DeBERTa-v3+CRF (66.12 F1), validating the effectiveness and robustness of the proposed method for entity recognition tasks in this domain.\u003c/p\u003e","manuscriptTitle":"PipeMoE-NER: MoE-LoRA Expert Adaptation and Three-Stage Chain-of-Thought for Pipeline Safety NER","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-15 22:47:17","doi":"10.21203/rs.3.rs-9148456/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-01T02:50:13+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-17T15:54:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"246102360203078295936178862205109718225","date":"2026-04-12T12:56:40+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-10T10:18:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"42719204206633421846709873208987502360","date":"2026-04-10T09:09:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"167609341276733015261761515301401386481","date":"2026-04-08T12:36:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"40699541581674437961713032746847343065","date":"2026-04-08T09:36:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"113977005222142528819081090193299959022","date":"2026-04-08T08:39:49+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-08T08:09:10+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-06T12:24:37+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-21T03:36:25+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-21T03:35:59+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-17T11:38:10+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":"9c6d2d26-49c9-407c-9950-f13519ae6082","owner":[],"postedDate":"April 15th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-01T02:50:13+00:00","index":87,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66157335,"name":"Physical sciences/Engineering"},{"id":66157336,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-15T22:47:17+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-15 22:47:17","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9148456","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9148456","identity":"rs-9148456","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}