Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision

ArXi:2604.06723v1 Announce Type: cross In today's AI-assisted software engineering landscape, developers increasingly depend on LLMs that are highly capable, yet inherently imperfect. The tendency of these models to produce incorrect outputs can reduce developer productivity. To this end, a canonical mitigation method is to provide calibrated confidence scores that faithfully reflect their likelihood of correctness at the instance-level.