2 papers
cs.SE2024
Exploring the Potential of Conversational Test Suite Based Program Repair on SWE-bench
Anton Cheshkov, Pavel Zadorozhny, Rodion Levichev +2
Automatic program repair at project level may open yet to be seen opportunities in various fields of human activity. Since the SWE-Bench challenge was presented, we have seen numer…
cs.CR2024
Finetuning Large Language Models for Vulnerability Detection
Alexey Shestov, Rodion Levichev, Ravil Mussabayev +3
This paper presents the results of finetuning large language models (LLMs) for the task of detecting vulnerabilities in source code. We leverage WizardCoder, a recent improvement o…