{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:308332575"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:308332575","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Apsauga nuo apgaulingų šablonų automatiškai su didžiaisiais kalbos modeliais parenkant naudotojui palankius slapukus /","abstract":"This thesis examines the use of large language models (LLMs) for automatically handling website cookie consent dialogs. A Chrome browser extension prototype was developed to analyse visible cookie consent dialog text and controls, select the most privacy­friendly action, and execute it in one or two clicks when it is safe to do so. The solution combines LLM­based interpretation with deterministic validation that prevents unreliable or privacy­unfriendly actions. The prototype was evaluated on 41 manually checked Lithuanian websites, comparing cloudbased OpenAI models, the local in­browser Gemini Nano provider, and the rule­based „Consent­OMatic“ extension. gpt-5.5 achieved the best result, while gpt-5.4-nano provided the fastest practical compromise. The results show that an LLM­based approach can adapt better to non­standard and Lithuanian cookie consent dialogs than solutions based only on preconfigured Consent Management Platform (CMP) rules.","abstract_html":"This thesis examines the use of large language models (LLMs) for automatically handling website cookie consent dialogs. A Chrome browser extension prototype was developed to analyse visible cookie consent dialog text and controls, select the most privacy­friendly action, and execute it in one or two clicks when it is safe to do so. The solution combines LLM­based interpretation with deterministic validation that prevents unreliable or privacy­unfriendly actions. The prototype was evaluated on 41 manually checked Lithuanian websites, comparing cloudbased OpenAI models, the local in­browser Gemini Nano provider, and the rule­based „Consent­OMatic“ extension. gpt-5.5 achieved the best result, while gpt-5.4-nano provided the fastest practical compromise. The results show that an LLM­based approach can adapt better to non­standard and Lithuanian cookie consent dialogs than solutions based only on preconfigured Consent Management Platform (CMP) rules.","abstract_has_math":false,"creators":["Bučelis, Jokūbas,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-19T10:12:52Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD308332575&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD308332575&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A308332575","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Bučelis, Jokūbas,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:308332575/308332575.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD308332575&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This thesis examines the use of large language models (LLMs) for automatically handling website cookie consent dialogs. A Chrome browser extension prototype was developed to analyse visible cookie consent dialog text and controls, select the most privacy­friendly action, and execute it in one or two clicks when it is safe to do so. The solution combines LLM­based interpretation with deterministic validation that prevents unreliable or privacy­unfriendly actions. The prototype was evaluated on 41 manually checked Lithuanian websites, comparing cloudbased OpenAI models, the local in­browser Gemini Nano provider, and the rule­based „Consent­OMatic“ extension. gpt-5.5 achieved the best result, while gpt-5.4-nano provided the fastest practical compromise. The results show that an LLM­based approach can adapt better to non­standard and Lithuanian cookie consent dialogs than solutions based only on preconfigured Consent Management Platform (CMP) rules."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Apsauga nuo apgaulingų šablonų automatiškai su didžiaisiais kalbos modeliais parenkant naudotojui palankius slapukus /","Protection against deceptive templates automatically with large language models by selecting user-friendly cookies."]}]}],"canonical_facts":{"dc:creator":["Bučelis, Jokūbas,"],"dc:date":["2026"],"dc:description":["This thesis examines the use of large language models (LLMs) for automatically handling website cookie consent dialogs. A Chrome browser extension prototype was developed to analyse visible cookie consent dialog text and controls, select the most privacy­friendly action, and execute it in one or two clicks when it is safe to do so. The solution combines LLM­based interpretation with deterministic validation that prevents unreliable or privacy­unfriendly actions. The prototype was evaluated on 41 manually checked Lithuanian websites, comparing cloudbased OpenAI models, the local in­browser Gemini Nano provider, and the rule­based „Consent­OMatic“ extension. gpt-5.5 achieved the best result, while gpt-5.4-nano provided the fastest practical compromise. The results show that an LLM­based approach can adapt better to non­standard and Lithuanian cookie consent dialogs than solutions based only on preconfigured Consent Management Platform (CMP) rules."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD308332575&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:308332575/308332575.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Apsauga nuo apgaulingų šablonų automatiškai su didžiaisiais kalbos modeliais parenkant naudotojui palankius slapukus /","Protection against deceptive templates automatically with large language models by selecting user-friendly cookies."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:12:52Z"}