Mitigating Implicit Hallucinations in Large Language Models Based on Progressive Prompt Chains

Mitigating Implicit Hallucinations in Large Language Models Based on Progressive Prompt Chains | 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 Mitigating Implicit Hallucinations in Large Language Models Based on Progressive Prompt Chains ChunYan Wang, Yue Wu, Jian Zhong This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8382656/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 The phenomenon of hallucinations in large language models (LLMs) refers to the generation of text that appears contextually coherent yet contains factual inaccuracies or logical inconsistencies. While explicit hallucinations typically refer to direct and verifiable, implicit hallucinations – subtle inaccuracies based on commonsense logic – prove more challenging to discern. This paper categorizes hallucinations into explicit and implicit types, with a focus on mitigating the critical issue of implicit hallucinations. To enhance LLMs’ self-awareness in detecting subtler inaccuracies, we begin with crowdsourced experiments aimed at identifying the most challenging type of hallucination: commonsense logic hallucinations. Based on these insights, we propose a novel framework utilizing progressive prompt chains. This framework has two interconnected phases. In the first phase, we extract core entities from user queries and link them to external knowledge bases to retrieve relevant contextual summaries. In the second phase, we implement multi-phase self-validation prompting, which enables iterative refinement of responses by applying truthfulness discrimination. Our extensive experiments across ten LLMs and two benchmark datasets demonstrate that the progressive prompt chains framework achieves an impressive 93% accuracy in self-assessing answer authenticity. Additionally, it improves answer generation quality accuracy by 41.6% compared to traditional prompting methods. Large Language Model Hallucination Implicit Hallucination Progressive Prompt Chains Detection and Mitigation Full Text Additional Declarations No competing interests reported. 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-8382656","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":564158855,"identity":"eeb5e5d2-a78c-4379-a4cd-6ce9f17b0a55","order_by":0,"name":"ChunYan Wang","email":"","orcid":"","institution":"Xhu University","correspondingAuthor":false,"prefix":"","firstName":"ChunYan","middleName":"","lastName":"Wang","suffix":""},{"id":564158856,"identity":"e3e4c560-bfb8-4a13-bdc0-bdd195a52485","order_by":1,"name":"Yue Wu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYNCCCgYGNnYGBmYw5wBRWs4AtTCTpIWxjQGsnjgtBjdyzCQ+ztsmz8fMwCZd2MYgx3cjgfFzAQEtkjO33TZsY2ZgNp7ZxmAseSOBWXoGHi1mQC3SvNtuMwK1MD7mbWNI3HAjgY2Zh5CWv3Nu2wO1MBwGaqknTgtjw+1EmC0JBoS02J95VmzZc+x2chszY7MxzzkJw5lnHjZL49Mi2Z688caPmtu289ubj0nzlNnI8x1PPvgZnxYGBg4DKIOxAUhIwBj4APsDAgpGwSgYBaNgxAMASM1EsXKZo6UAAAAASUVORK5CYII=","orcid":"","institution":"Xhu University","correspondingAuthor":true,"prefix":"","firstName":"Yue","middleName":"","lastName":"Wu","suffix":""},{"id":564158857,"identity":"82ae3b70-7043-4068-98c6-f6f0215650b3","order_by":2,"name":"Jian Zhong","email":"","orcid":"","institution":"Xhu University","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Zhong","suffix":""}],"badges":[],"createdAt":"2025-12-17 07:23:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8382656/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8382656/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98921025,"identity":"7244745e-26bb-495e-ad6e-661075a42cd3","added_by":"auto","created_at":"2025-12-24 06:14:53","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1790362,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8382656/v1/83c6691fd56aa9e68e940906.pdf"},{"id":98921024,"identity":"6ced1ea2-2ddb-4f63-bc2e-6ca4beb6a4fe","added_by":"auto","created_at":"2025-12-24 06:14:53","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4860,"visible":true,"origin":"","legend":"","description":"","filename":"8436dd9a1be249cfaea0139e900a2345.json","url":"https://assets-eu.researchsquare.com/files/rs-8382656/v1/13904acd71da2801b526728b.json"},{"id":102296561,"identity":"18726928-1bcd-4c97-af7d-d3188e3f5486","added_by":"auto","created_at":"2026-02-10 10:20:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1405516,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8382656/v1_covered_423a7179-89a5-44b4-b666-e6f2d235b028.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Mitigating Implicit Hallucinations in Large Language Models Based on Progressive Prompt Chains","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"Large Language Model Hallucination, Implicit Hallucination, Progressive Prompt Chains, Detection and Mitigation","lastPublishedDoi":"10.21203/rs.3.rs-8382656/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8382656/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The phenomenon of hallucinations in large language models (LLMs) refers to the generation of text that appears contextually coherent yet contains factual inaccuracies or logical inconsistencies. While explicit hallucinations typically refer to direct and verifiable, implicit hallucinations – subtle inaccuracies based on commonsense logic – prove more challenging to discern. This paper categorizes hallucinations into explicit and implicit types, with a focus on mitigating the critical issue of implicit hallucinations. To enhance LLMs’ self-awareness in detecting subtler inaccuracies, we begin with crowdsourced experiments aimed at identifying the most challenging type of hallucination: commonsense logic hallucinations. Based on these insights, we propose a novel framework utilizing progressive prompt chains. This framework has two interconnected phases. In the first phase, we extract core entities from user queries and link them to external knowledge bases to retrieve relevant contextual summaries. In the second phase, we implement multi-phase self-validation prompting, which enables iterative refinement of responses by applying truthfulness discrimination. Our extensive experiments across ten LLMs and two benchmark datasets demonstrate that the progressive prompt chains framework achieves an impressive 93% accuracy in self-assessing answer authenticity. Additionally, it improves answer generation quality accuracy by 41.6% compared to traditional prompting methods.","manuscriptTitle":"Mitigating Implicit Hallucinations in Large Language Models Based on Progressive Prompt Chains","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-24 06:14:49","doi":"10.21203/rs.3.rs-8382656/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":"c53163b0-2bc3-4376-a626-e891f1d8ee5a","owner":[],"postedDate":"December 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-08T00:38:33+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-24 06:14:49","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8382656","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8382656","identity":"rs-8382656","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}