Preprint
Jul 2026
When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation
It is suggested that cheap uncertainty estimators are insufficient on their own to improve code correctness, and that their practical value lies in serving as gating signals for costlier execution-based correction loops rather than as standalone substitutes for verification.
Pranav Rakasi, Maanas Lalwani, A. Srivastava et al.
· 0 citations