Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning
This work proposes a framework for quality-aware preference learning that guides LLMs toward generating criteria-compliant code and introduces a hybrid optimization objective that combines ranking loss with language modeling loss and KL divergence to enable effective comparative optimization.
Liang Lu, Yuan Jiang, Christoph Treude et al.
· 2 citations