prikaz prve stranice dokumenta Korištenje velikih jezičnih modela u ocjenjivanju programskog koda studenata
No public access
undergraduate thesis
Korištenje velikih jezičnih modela u ocjenjivanju programskog koda studenata
2024. urn:nbn:hr:168:560143
Gašpar, Sara
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Gašpar, S. (2024). Korištenje velikih jezičnih modela u ocjenjivanju programskog koda studenata (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:560143

Gašpar, Sara. "Korištenje velikih jezičnih modela u ocjenjivanju programskog koda studenata." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:560143

Gašpar, Sara. "Korištenje velikih jezičnih modela u ocjenjivanju programskog koda studenata." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:560143

Gašpar, S. (2024). 'Korištenje velikih jezičnih modela u ocjenjivanju programskog koda studenata', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:560143

Gašpar S. Korištenje velikih jezičnih modela u ocjenjivanju programskog koda studenata [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2024 [cited 2024 December 25] Available at: https://urn.nsk.hr/urn:nbn:hr:168:560143

S. Gašpar, "Korištenje velikih jezičnih modela u ocjenjivanju programskog koda studenata", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:168:560143

Please login to the repository to save this object to your list.
Metadata
TitleKorištenje velikih jezičnih modela u ocjenjivanju programskog koda studenata
Title (english)Using Large Language Models in evaluating student programming code
AuthorSara Gašpar
MentorLjiljana Brkić (mentor)
Committee memberLjiljana Brkić (predsjednik povjerenstva)
Committee memberAgneza Krajna (član povjerenstva)
Committee memberMelita Fertalj (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2024-06-27, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovim radom je cilj bio istražiti uspješnost velikih jezičnih modela u ocjenjivanju programskog koda studenata na rješenjima zadataka iz ispita. ChatGPT i Gemini su LLM- ovi korišteni u istraživanju. Opisan je skup podataka za analizu, veliki jezični modeli i korištena metodologija. Provedene su analize bodova i povratnih informacija koje su studentima dodijelili veliki jezični modeli u usporedbi s bodovima prethodno dodijeljenim od strane nastavnog osoblja s predmeta. Predložene su mjere kojima se ocijenila uspješnost LLM-ova u ocjenjivanju.
Abstract (english)
The aim of this work was to investigate the success of large language models in evaluating the students' program code on the solutions to the exam tasks. The LLMs used in the research are ChatGPT and Gemini. The work described the data set for the analysis, the large language models and the used methodology. Analyzes of the scores and feedback awarded to students by the large language models were compared to the scores previously awarded by the subject teaching staff. Measures were proposed to evaluate the success of LLMs in evaluation.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:560143
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2024-10-12 20:37:44