From If-Statements to ML Pipelines: Revisiting Bias in Code-Generation

ArXi:2604.21716v1 Announce Type: new Prior work evaluates code generation bias primarily through simple conditional statements, which represent only a narrow slice of real-world programming and reveal solely overt, explicitly encoded bias. We nstrate that this approach dramatically underestimates bias in practice by examining a realistic task: generating machine learning (ML) pipelines. Testing both code-specialized and general-instruction large language models, we find that generated pipelines exhibit significant bias during feature selection.