<div class="csl-bib-body">
<div class="csl-entry">Eniser, H. F., Wüstholz, V., & Christaki, M. (2023). <i>Automatically Testing Functional Properties of Code Translation Models</i>. https://doi.org/10.48550/arXiv.2309.12813</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/188809
-
dc.description.abstract
Large language models are becoming increasingly practical for translating code across programming languages, a process known as transpiling. Even though automated transpilation significantly boosts developer productivity, a key concern is whether the generated code is correct. Existing work initially used manually crafted test suites to test the translations of a small corpus of programs; these test suites were later automated. In contrast, we devise the first approach for automated, functional, property-based testing of code translation models. Our general, user-provided specifications about the transpiled code capture a range of properties, from purely syntactic to purely semantic ones. As shown by our experiments, this approach is very effective in detecting property violations in popular code translation models, and therefore, in evaluating model quality with respect to given properties. We also go a step further and explore the usage scenario where a user simply aims to obtain a correct translation of some code with respect to certain properties without necessarily being concerned about the overall quality of the model. To this purpose, we develop the first property-guided search procedure for code translation models, where a model is repeatedly queried with slightly different parameters to produce alternative and potentially more correct translations. Our results show that this search procedure helps to obtain significantly better code translations.
en
dc.language.iso
en
-
dc.subject
metamorphic testing
en
dc.subject
code translation models
en
dc.title
Automatically Testing Functional Properties of Code Translation Models
en
dc.type
Report
en
dc.type
Bericht
de
dc.contributor.affiliation
MPI-SWS, Germany
-
dc.contributor.affiliation
ConsenSys, Austria
-
dc.type.category
Technical Report
-
tuw.researchTopic.id
I4
-
tuw.researchTopic.name
Information Systems Engineering
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E194-01 - Forschungsbereich Software Engineering
-
tuw.publisher.doi
10.48550/arXiv.2309.12813
-
dc.description.numberOfPages
13
-
tuw.author.orcid
0000-0003-1496-1104
-
tuw.author.orcid
0000-0002-2649-1958
-
wb.sciencebranch
Informatik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.value
100
-
item.languageiso639-1
en
-
item.cerifentitytype
Publications
-
item.fulltext
no Fulltext
-
item.grantfulltext
none
-
item.openairecristype
http://purl.org/coar/resource_type/c_18gh
-
item.openairetype
technical report
-
crisitem.author.dept
MPI-SWS, Germany
-
crisitem.author.dept
ConsenSys, Austria
-
crisitem.author.dept
E194-01 - Forschungsbereich Information und Software Engineering
-
crisitem.author.orcid
0000-0003-1496-1104
-
crisitem.author.orcid
0000-0002-2649-1958
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering