A data synthesis framework generates four syntax/semantics code pair types, and fine-tuning embedding models on the resulting datasets improves code clone detection, functional consistency, and retrieval.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking
A data synthesis framework generates four syntax/semantics code pair types, and fine-tuning embedding models on the resulting datasets improves code clone detection, functional consistency, and retrieval.