When Uncertainty Isn't Enough
An Empirical Study of Self-Correction in Code Generation: Large language models for code generation often produce incorrect solutions without reliable indicators of failure. We study whether uncertainty estimation methods developed for natural language transfer to code generation, and whether such signals can improve code generation via selective self-correction. We evaluate five uncertainty methods: mean token...
Source Brief
When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation: Large language models for code generation often produce incorrect solutions without reliable indicators of failure. We study whether uncertainty estimation methods developed for natural language transfer to code generation, and whether such signals can improve code generation via selective self-correction. We evaluate five uncertainty methods: mean token...