Local Platt scaling on three fine-grained confidence scores reduces calibration error for LLM-based automated code revision across tasks and models compared to global scaling alone.
On calibration of pre-trained code models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision
Local Platt scaling on three fine-grained confidence scores reduces calibration error for LLM-based automated code revision across tasks and models compared to global scaling alone.