{"paper_id":"1559335d-6ca8-4377-9239-b9bb03e3a5ff","body_text":"LLM model for ESG Reporting | 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a Preprint Cite Share Download PDF Research Article LLM model for ESG Reporting Al Khan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8628271/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 Sustainability reporting, though an opportunity for organisations to demonstrate their performance with respect to environmental, social, and governance perspectives, has requirements in the transparency of the record, strategy, and policy-making process. However, preparation by way of collection and compilation of data from the reports sometimes poses a lot of difficulties resulting in discrepancies and anomalies. The contribution of this work is a system that applies AI, and in particular, Natural Language Processing, to extract the data of a sustainability report using unstructured reports. An application based on GPT-3 developed by OpenAI transforms a given report from an unstructured format within PDF documents to a structured format according to the ESRS. The operational framework of the system encompasses the following main steps: reading PDF files, text normalization, data categorization, executing requests concurrently, and final refinements. Efficiency in the system is measured by cosine similarity metrics, which check how well the output of the system correlates with manually extracted data. High values of correlation obtained ensure that this system has huge potential to advance sustainability reporting practices. This is one major initiative in realizing transparent. Artificial Intelligence and Machine Learning LLM Sustainability report GPT Artificial Intelligence Full Text Additional Declarations The authors declare no competing interests. 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-8628271\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":576155851,\"identity\":\"90095137-ed06-4c74-b500-32e181d60a2b\",\"order_by\":0,\"name\":\"Al Khan\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYDACHh4QKSFnAOYZWBCtxcLYgIEZpEWCaC0ViRvAWhiI0GLOc/bg5wIGifTt7P1HN/wokGDgb+9OwKvFsrcvWXoGg0Tuzp7DbDd7gA6TOHN2A14tBud5DKR5gFo23Ehmu8ED1GIAZBPSYvwbqCXdAKjl5h+itJztMQPZkgDScpsoWyx7zphZA7UYbjhz2Oy2jIEED0G/mPPkGN/mYaiTNzje+Ozmmz82cvztvQQcBiIY/yEEePAqh2sZBaNgFIyCUYAXAACuMT46V7Rw3wAAAABJRU5ErkJggg==\",\"orcid\":\"\",\"institution\":\"\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Al\",\"middleName\":\"\",\"lastName\":\"Khan\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2026-01-17 21:21:42\",\"currentVersionCode\":1,\"declarations\":{\"humanSubjects\":false,\"vertebrateSubjects\":false,\"conflictsOfInterestStatement\":false,\"humanSubjectEthicalGuidelines\":false,\"humanSubjectConsent\":false,\"humanSubjectClinicalTrial\":false,\"humanSubjectCaseReport\":false,\"vertebrateSubjectEthicalGuidelines\":false},\"doi\":\"10.21203/rs.3.rs-8628271/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-8628271/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":100826452,\"identity\":\"89bf8180-32ca-469c-9067-cde70faa57b2\",\"added_by\":\"auto\",\"created_at\":\"2026-01-21 19:19:46\",\"extension\":\"doc\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":496640,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"preprints193577manuscript.doc\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/d036e2f1bf19778381472635.doc\"},{\"id\":100826443,\"identity\":\"a8bbdb75-3b74-4e72-b2d3-3b61b68beb73\",\"added_by\":\"auto\",\"created_at\":\"2026-01-21 19:19:46\",\"extension\":\"json\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":342,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"rs8628271.json\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/d6bf14af93b04fab4fe4cc4b.json\"},{\"id\":100826448,\"identity\":\"56c3d347-c77f-45f4-b601-a3776c5ed3be\",\"added_by\":\"auto\",\"created_at\":\"2026-01-21 19:19:46\",\"extension\":\"xml\",\"order_by\":2,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":80874,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"rs86282710enriched.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/d30c91a76fc73244881e3903.xml\"},{\"id\":100858654,\"identity\":\"64ffb380-70d3-4687-8dc5-49f9a87d515e\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 07:24:33\",\"extension\":\"png\",\"order_by\":3,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":2279,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/b3a54be3905947c928b6ff53.png\"},{\"id\":100859230,\"identity\":\"151a96f2-c4bd-4836-83c3-dcc6d2b52eea\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 07:25:45\",\"extension\":\"jpeg\",\"order_by\":4,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":175928,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage2.jpeg\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/338c72700ada61a4c4f7aca1.jpeg\"},{\"id\":100858679,\"identity\":\"5db70890-bd9c-4832-9c39-77dad98773e8\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 07:24:36\",\"extension\":\"png\",\"order_by\":5,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":29195,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/e277c96ad0d5834ccc729620.png\"},{\"id\":100858506,\"identity\":\"b2024deb-3807-4d75-a889-6c824e29aa58\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 07:24:23\",\"extension\":\"jpeg\",\"order_by\":6,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":123265,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage4.jpeg\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/360f49e5a5970a60bd86635e.jpeg\"},{\"id\":100858871,\"identity\":\"c2876438-e62d-448c-9b26-f1a08e1fec52\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 07:24:52\",\"extension\":\"png\",\"order_by\":7,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":39738,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage5.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/830a50c610e423b4191502fc.png\"},{\"id\":100826447,\"identity\":\"092dc5c0-fd65-40e1-9e38-f1543a301ed1\",\"added_by\":\"auto\",\"created_at\":\"2026-01-21 19:19:46\",\"extension\":\"png\",\"order_by\":8,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":584,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/f6d9ca27edbec7e8603a40b3.png\"},{\"id\":100858383,\"identity\":\"900c83bd-2694-4e31-9e4b-5e08f92351a6\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 07:24:14\",\"extension\":\"png\",\"order_by\":9,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":48796,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage2.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/c06286a3d0c97ab0fedad84d.png\"},{\"id\":100826455,\"identity\":\"02042e9a-22d5-4608-bd15-10606daf6424\",\"added_by\":\"auto\",\"created_at\":\"2026-01-21 19:19:47\",\"extension\":\"png\",\"order_by\":10,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":16426,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/b6b895582405845e1efd1151.png\"},{\"id\":100858488,\"identity\":\"df9e315c-03c2-456f-90f5-c12ba1123caa\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 07:24:22\",\"extension\":\"png\",\"order_by\":11,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":29059,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage4.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/f361b36fe656a44439256efd.png\"},{\"id\":100858496,\"identity\":\"2cbc8ac1-ec12-4c6d-9993-f60bd73f1dfe\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 07:24:22\",\"extension\":\"png\",\"order_by\":12,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":9626,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage5.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/8ad88a2979b31d8527a7055c.png\"},{\"id\":100826453,\"identity\":\"6e440f15-3700-4e1a-ad9e-25a38065e5cf\",\"added_by\":\"auto\",\"created_at\":\"2026-01-21 19:19:46\",\"extension\":\"xml\",\"order_by\":13,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":79419,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"rs86282710structuring.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/a652811b6f1f4b88b0302faf.xml\"},{\"id\":100858770,\"identity\":\"b36a79aa-db32-4f16-b381-551f7f30e172\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 07:24:45\",\"extension\":\"html\",\"order_by\":14,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":88664,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"earlyproof.html\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1/bf210da1a4ae8e32bf98794d.html\"},{\"id\":100859920,\"identity\":\"0dd70a1c-3ca9-4319-9359-eb531c0d56e6\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 07:34:22\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":442721,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"preprints193577manuscript.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8628271/v1_covered_6e3f6345-521c-43ec-b124-4718960c509b.pdf\"}],\"financialInterests\":\"The authors declare no competing interests.\",\"formattedTitle\":\"\\u003cp\\u003eLLM model for ESG Reporting\\u003c/p\\u003e\",\"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\":\"info@researchsquare.com\",\"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\":\"LLM, Sustainability report, GPT, Artificial Intelligence\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-8628271/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-8628271/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eSustainability reporting, though an opportunity for organisations to demonstrate their performance with respect to environmental, social, and governance perspectives, has requirements in the transparency of the record, strategy, and policy-making process. However, preparation by way of collection and compilation of data from the reports sometimes poses a lot of difficulties resulting in discrepancies and anomalies. The contribution of this work is a system that applies AI, and in particular, Natural Language Processing, to extract the data of a sustainability report using unstructured reports. An application based on GPT-3 developed by OpenAI transforms a given report from an unstructured format within PDF documents to a structured format according to the ESRS. The operational framework of the system encompasses the following main steps: reading PDF files, text normalization, data categorization, executing requests concurrently, and final refinements. Efficiency in the system is measured by cosine similarity metrics, which check how well the output of the system correlates with manually extracted data. High values of correlation obtained ensure that this system has huge potential to advance sustainability reporting practices. This is one major initiative in realizing transparent.\\u003c/p\\u003e\",\"manuscriptTitle\":\"LLM model for ESG Reporting\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2026-01-21 19:19:41\",\"doi\":\"10.21203/rs.3.rs-8628271/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"4747147e-3249-47b1-ade4-812a813f4262\",\"owner\":[],\"postedDate\":\"January 21st, 2026\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[{\"id\":61305129,\"name\":\"Artificial Intelligence and Machine Learning\"}],\"tags\":[],\"updatedAt\":\"2026-01-21T19:19:42+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2026-01-21 19:19:41\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-8628271\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-8628271\",\"identity\":\"rs-8628271\",\"version\":[\"v1\"]},\"buildId\":\"XKTyCvWXoU3ODBz1xrDgd\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}