Institutional Repository of Vilnius University
Apsauga nuo apgaulingų šablonų automatiškai su didžiaisiais kalbos modeliais parenkant naudotojui palankius slapukus /
Abstract
dc:descriptionThis 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.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Bučelis, Jokūbas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308332575&prefLang=en_US