Towards Trustworthy and Effective AI for Academic Policy Navigation: Human Evaluation of a Source-Aware, Domain-Optimized RAG-Based Chatbot

Towards Trustworthy and Effective AI for Academic Policy Navigation: Human Evaluation of a Source-Aware, Domain-Optimized RAG-Based Chatbot | 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 Towards Trustworthy and Effective AI for Academic Policy Navigation: Human Evaluation of a Source-Aware, Domain-Optimized RAG-Based Chatbot Sofia Meacham, Alireza Sharafzad This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7535973/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 Navigating institutional policies remains a challenge for students and staff due to complex legalistic language, hierarchical structures, and dispersed documentation. While Large Language Models (LLMs) such as GPT-4o offer fluent natural language capabilities, their susceptibility to hallucination limits their perceived trustworthiness in academic contexts where factual accuracy and traceability are critical. This study investigates how a combination of transparency-enhancing tactics—specifically, source citation and human-centered evaluation—and domain-specific performance strategies can support the development of more trustworthy and effective AI systems. We present a source-aware, Retrieval-Augmented Generation (RAG)-based chatbot designed to assist users in interpreting Bournemouth University’s Code of Practice for Research Degrees. The system integrates trust-building interventions with performance-enhancing techniques tailored to policy documents, including layout-aware chunking, hybrid self-reranking, and semantic vector search using Pinecone. Quantitative evaluation using the RAGAS framework and BERTScore shows a high faithfulness score (0.9597), outperforming baseline LLM responses. In a pilot user study with doctoral students, participants reported strong satisfaction with clarity (mean score: 3.60/4.0) and source attribution (92% accuracy). While not a complete solution for trustworthy AI, this work demonstrates how targeted design interventions—combining transparency and domain optimization—can enhance both trust and effectiveness in AI-assisted academic policy navigation. Retrieval-Augmented Generation Chatbot Academic Policy RAGAS evaluation 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-7535973","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":510308309,"identity":"5afb0620-8728-459e-bba6-cf17ddcbb76b","order_by":0,"name":"Sofia Meacham","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIiWNgGAWjYLACxgYGBn4JBJ8NQvEQ0CI5A85lJlKLwQ1itchPO3zww88ddtHGt5uPSVfusInml8g/9oChxo7B4MwBrFoMbqclS/aeSc7ddudYmuTZM2m5M2cksxswHEtmMDjbgF2LdI6BNGMbc+62Gzlmko1th3M33Ehmk2BgO8BgcB6Hw2bnf/7N2Fafu3kGWMt/qJZ/uLUw3M5hA9oCNFwCrOUARAtj2wHcDrudZmbZ23Y8d8adY8mWjW3JuTN7HptJJPYl80ji8L787OTHN362Vef2z24+eLOxzS63nz3xmcSHb3ZyfGcScLgMK0jAH5GjYBSMglEwCggAAKe5Yb4u3zN+AAAAAElFTkSuQmCC","orcid":"","institution":"Bournemouth University","correspondingAuthor":true,"prefix":"","firstName":"Sofia","middleName":"","lastName":"Meacham","suffix":""},{"id":510308310,"identity":"bc67fa3e-5fa6-4c97-ab48-db4388caf09e","order_by":1,"name":"Alireza Sharafzad","email":"","orcid":"","institution":"Bournemouth University","correspondingAuthor":false,"prefix":"","firstName":"Alireza","middleName":"","lastName":"Sharafzad","suffix":""}],"badges":[],"createdAt":"2025-09-04 12:08:37","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7535973/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7535973/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90716215,"identity":"fff25535-a7f7-41f9-8ba6-b610f9ac1ca8","added_by":"auto","created_at":"2025-09-06 09:16:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1118198,"visible":true,"origin":"","legend":"","description":"","filename":"LLMandPolicieschatbot.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7535973/v1_covered_2cf5b906-9607-4407-94dc-514d0c5946c5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Towards Trustworthy and Effective AI for Academic Policy Navigation: Human Evaluation of a Source-Aware, Domain-Optimized RAG-Based Chatbot","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Retrieval-Augmented Generation, Chatbot, Academic Policy, RAGAS evaluation","lastPublishedDoi":"10.21203/rs.3.rs-7535973/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7535973/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eNavigating institutional policies remains a challenge for students and staff due to complex legalistic language, hierarchical structures, and dispersed documentation. While Large Language Models (LLMs) such as GPT-4o offer fluent natural language capabilities, their susceptibility to hallucination limits their perceived trustworthiness in academic contexts where factual accuracy and traceability are critical. This study investigates how a combination of transparency-enhancing tactics\u0026mdash;specifically, source citation and human-centered evaluation\u0026mdash;and domain-specific performance strategies can support the development of more trustworthy and effective AI systems. We present a source-aware, Retrieval-Augmented Generation (RAG)-based chatbot designed to assist users in interpreting Bournemouth University\u0026rsquo;s Code of Practice for Research Degrees. The system integrates trust-building interventions with performance-enhancing techniques tailored to policy documents, including layout-aware chunking, hybrid self-reranking, and semantic vector search using Pinecone. Quantitative evaluation using the RAGAS framework and BERTScore shows a high faithfulness score (0.9597), outperforming baseline LLM responses. In a pilot user study with doctoral students, participants reported strong satisfaction with clarity (mean score: 3.60/4.0) and source attribution (92% accuracy). While not a complete solution for trustworthy AI, this work demonstrates how targeted design interventions\u0026mdash;combining transparency and domain optimization\u0026mdash;can enhance both trust and effectiveness in AI-assisted academic policy navigation.\u003c/p\u003e","manuscriptTitle":"Towards Trustworthy and Effective AI for Academic Policy Navigation: Human Evaluation of a Source-Aware, Domain-Optimized RAG-Based Chatbot","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-05 17:02:45","doi":"10.21203/rs.3.rs-7535973/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":"d82ea46c-a47e-443a-b474-ab6e095f371b","owner":[],"postedDate":"September 5th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-06T09:08:23+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-05 17:02:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7535973","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7535973","identity":"rs-7535973","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}