Towards a Human-in-the-Loop Framework for Reliable Patch Evaluation Using an LLM-as-a-Judge

Reliable evaluation is crucial for advancing Automated Program Repair (APR), but prevailing benchmarks rely on execution-based evaluation metrics (pass@k), which fail to capture true patch validity. Determining validity can require costly manual annotation. To reduce this cost, we introduce a human-in-the-loop framework to LLM-based patch validity judgment. Driven by the observation that human judgment is better aligned when using a shared rubric, we first employ an LLM to generate a per-bug rubric, followed by a one-time human review and optional refinement to this rubric, and then employ an LLM to judge patches using the refined rubric. We apply this framework to assign binary validity labels to patches for issues found by Google sanitizer tools. Our results show that this framework yields substantial agreement with human consensus (Cohen’s kappa 0.75), high recall (0.94) and high precision (0.80) when considering patches that have unanimous agreement from 3 human raters on the validity labels. On the full dataset including patches where human raters disagree, we find this approach can still be further improved (Cohen’s kappa 0.57, recall 0.93, precision 0.65) and identify possible future directions.