Researchers have developed Sliceformer, a new method for static program slicing that uses language models to identify relevant code segments. This approach addresses limitations in existing learning-based techniques by improving dependency modeling through dataflow-aware pretraining and preventing inaccurate outputs with constrained decoding. Evaluations on Java and Python benchmarks show Sliceformer significantly outperforms current methods, achieving up to a 22% increase in ExactMatch accuracy. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Improves automated code analysis accuracy, potentially aiding developers in debugging and understanding complex codebases.
RANK_REASON Academic paper introducing a novel method for static program slicing.