A code model can improve its one-shot code generation by iteratively training on its own best solutions and external critiques of its weak solutions, using only SFT and 80K instructions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation
A code model can improve its one-shot code generation by iteratively training on its own best solutions and external critiques of its weak solutions, using only SFT and 80K instructions.