Control Models for In-IDE Code Completion
Year: 2026
Type: conference-paper
Abstract: We introduce control models for LLM-powered code completion in JetBrains IDEs: ML classifiers which trigger inference and filter the generated suggestions to better align them with users and reduce unnecessary requests. To this end, we evaluate boosting- and transformer-based architectures on an offline dataset of real code completions with n = 98 users. We further evaluate the offline classification performance of our boosting-based approach on a range of syntactically diverse languages; and perform an A/B study in a production environment where they improve completion efficiency and quality metrics. With this study, we hope to demonstrate the potential in using auxiliary models for smarter in-IDE integration of LLM-driven features, highlight fruitful future directions, and open problems.
Authors: Aral de Moor, Yana Hrynevich, Hleb Badzeika, Vladyslav Furda, Marko Kojic, Artem Savelev, Kostadin Cvejoski, Darya Rovdo, Ekaterina Garanina
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W7126083117
FWCI:
Cites:
Cited by:
Related to: