一作ACL 2026Findings· Findings of ACL
I ntent C oding: Amplifying User Intent in Code Generation
Zheng Fang · Yihong Dong · Lili Mou · Dongming Jin · Zhi Jin · Ge Li
摘要
Large Language Models (LLMs) have shown strong capabilities in code generation, but their adherence to fine-grained user intent with multiple constraints remains a significant challenge. Our empirical analysis reveals two key observations: 1) Model performance deteriorates quickly as the number o...