Improving code completion interpretability with concept-level intervention

doi:10.1016/j.infsof.2026.108309

Improving code completion interpretability with concept-level intervention

2026-09-04

0

PRE

AI

DOI：10.1016/j.infsof.2026.108309

Original

Original request for help

Save

Abstract

En 中文

Code pre-trained models have been widely adopted in automated code completion tasks. However, traditional completion approaches primarily rely on sequential modeling, which often overlooks the rich syntactic and structural information inherent in source code.

Improving code completion interpretability with concept-level intervention

Abstract

Journal

Organization

Cited Papers