| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Razlaga odločitev umetne inteligence v obliki pogovorov z velikimi jezikovnimi modeli : magistrsko delo
Authors:ID Sernec, Jan (Author)
ID Karakatič, Sašo (Mentor) More about this mentor... New window
ID Brdnik, Saša (Comentor)
Files:.pdf MAG_Sernec_Jan_2025.pdf (2,10 MB)
MD5: 19FE27753FFFAABEB574B58DB936F850
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Razlaga odločitev, sprejetih s pomočjo umetne inteligence, postaja vse pomembnejša, saj umetna inteligenca danes aktivno sodeluje v sistemih, ki se uporabljajo v kritičnih področjih, kot so medicina, energetika, bančništvo. Take odločitve imajo pomemben vpliv na naše življenje, zato je ključnega pomena, da so uporabnikom razumljive in transparentne. Čeprav so statične razlage kot na primer, SHAP in LIME, v praksi še vedno najpogosteje uporabljene, se pogosto izkaže, da ne naslovijo vseh vprašanj in dvomov uporabnikov. Zaradi tega postajajo vse bolj relevantne interaktivne razlage, ki omogočajo dialog z velikim jezikovnim modelom in s tem prilagojeno, pojasnjevalno izkušnjo. V okviru magistrskega dela smo izvedli eksperiment, v katerem smo primerjali vpliv statičnih in interaktivnih razlag na uporabniško izkušnjo. Za ta namen smo razvili spletno orodje, ki omogoča predstavitev obeh tipov razlag. Uporabniško razumevanje odločitev smo merili s pomočjo vedenjskih nalog, oblikovanih na podlagi metod za merjenje mentalnih modelov. Rezultati eksperimenta nudijo pomemben vpogled v to, kako uporabniki zaznavajo in vrednotijo različne oblike razlag ter razkrivajo njihove preference pri razumevanju odločitev umetne inteligence.
Keywords:veliki jezikovni modeli, interaktivne razlage, statične razlage, razlaga odločitev, razložljiva umetna inteligenca
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[J. Sernec]
Year of publishing:2025
Number of pages:1 spletni vir (1 datoteka PDF (XV, 99 str.))
PID:20.500.12556/DKUM-96062 New window
UDC:004.8:519.766(043.2)
COBISS.SI-ID:266786307 New window
Publication date in DKUM:22.12.2025
Views:236
Downloads:88
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:28.11.2025

Secondary language

Language:English
Title:Conversational explanations of AI decisions using Large Language Models
Abstract:Explaining decisions made with the help of artificial intelligence is becoming increasingly important, as AI systems are now actively involved in critical domains such as healthcare, energy, and banking. These decisions can significantly influence our lives, making it essential that they are transparent and understandable to users. The currently prevailing static explanations often fail to address all user questions, which is why interactive explanations where the user engages in a dialogue with a large language model are gaining relevance. In this master’s thesis, we conducted an experiment comparing the impact of static and interactive explanations on the user experience. We developed a tool that was used to carry out the experiment with both types of explanations. User understanding of AI decisions was measured through tasks derived from methods used for assessing mental models. The results of the experiment provided insight into user preferences regarding different types of explanations.
Keywords:large language models, interactive explanations, static explanations, decision explanation, explainable artificial intelligence


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica