一作ACL 2026Findings· Findings of ACL
C ode R ise: Bootstrapping LLM s for Ultra Low-Resource Programming Languages via Progressive Self-Refinement Curriculum
Tengfei Wen · Xuanang Chen · Ben He · Xiaoliang Cong · Le Sun
摘要
Large Language Models (LLMs) struggle with code generation for Ultra Low-Resource Programming Languages (ULRPLs) due to the scarcity of training data. Existing synthetic data generation methods fail in this context, suffering from a severe cold-start problem and resulting in samples that lack div...