Counterexample guided program repair using zero-shot learning and MaxSAT-based fault localization
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F25%3A00387612" target="_blank" >RIV/68407700:21730/25:00387612 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1609/aaai.v39i1.32046" target="_blank" >https://doi.org/10.1609/aaai.v39i1.32046</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1609/aaai.v39i1.32046" target="_blank" >10.1609/aaai.v39i1.32046</a>
Alternative languages
Result language
angličtina
Original language name
Counterexample guided program repair using zero-shot learning and MaxSAT-based fault localization
Original language description
Automated Program Repair (APR) for introductory programming assignments (IPAS) is motivated by the large number of student enrollments in programming courses each year. Since providing feedback on programming assignments requires substantial time and effort from faculty, personalized automated feedback often involves suggesting repairs to students' programs. Symbolic semantic repair approaches, which rely on Formal Methods (FM), check a program's execution against a test suite or reference solution, are effective but limited. These tools excel at identifying buggy parts but can only fix programs if the correct implementation and the faulty one share the same control flow graph. Conversely, Large Language Models (LLMS) are used for program repair but often make extensive rewrites instead of minimal adjustments. This tends to lead to more invasive fixes, making it harder for students to learn from their mistakes. In summary, LLMS excel at completing strings, while FM-based fault localization excel at identifying buggy parts of a program.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 39th AAAI Conference on Artificial Intelligence
ISBN
978-1-57735-897-8
ISSN
2159-5399
e-ISSN
2374-3468
Number of pages
9
Pages from-to
649-657
Publisher name
AAAI Press
Place of publication
Menlo Park
Event location
Philadelphia
Event date
Feb 27, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001478149100073