Developing of Mini-Scientific Chatbot based on Transformers and LLMs

dc.contributor.advisorSaid, Gadri
dc.contributor.authorRoqiya, Allal
dc.contributor.authorFaten Aichaoui
dc.date.accessioned2026-07-07T12:59:38Z
dc.date.issued2026-06-10
dc.description.abstractThis thesis presents MedSci-GPT, a lightweight multilingual scientific chatbot using a hybrid architecture: GPT-4o API (primary) and fine-tuned Phi-2 (fallback). LoRA (rank 8, alpha 16) was applied on scientific QA datasets. A web app was built with PHP, MySQL, HTML/CSS/JS supporting authentication, conversation management, and Arabic/English/French. Evaluation shows Phi-2 achieves 76% accuracy (0.8s) and GPT-4o 82% (1.8s), proving lightweight scientific assistants run on standard hardware.
dc.identifier.urihttps://depot.univ-msila.dz/handle/123456789/48862
dc.language.isoen
dc.publisherUniversity of M'sila
dc.subjectLarge Language Models
dc.subjectScientific Chatbot
dc.subjectFine-tuning
dc.subjectLoRA
dc.subjectGPT-4o
dc.subjectPhi- 2
dc.subjectMultilingual
dc.subjectArabic NLP
dc.subjectQuestion Answering
dc.subjectTransformer
dc.titleDeveloping of Mini-Scientific Chatbot based on Transformers and LLMs
dc.typeThesis

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Allal&Aichaoui_MedSci.Chatbot FullThesis.pdf
Size:
3.41 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections