CURE applies contrastive unlearning to reduce deprecated API usage in code LLMs and improve correct replacements on a benchmark dataset while preserving general performance.
An empirical study on the impact of refactoring activities on evolving client-used apis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Knowledge Alignment in Code LLMs: Contrastive Unlearning for Evolving APIs
CURE applies contrastive unlearning to reduce deprecated API usage in code LLMs and improve correct replacements on a benchmark dataset while preserving general performance.