AI RESEARCH
A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair
arXiv CS.AI
•
ArXi:2604.21579v1 Announce Type: cross LLM-based automated program repair (APR) techniques have shown promising results in reducing debugging costs. However, prior results can be affected by data leakage: large language models (LLMs) may memorize bug fixes when evaluation benchmarks overlap with their pre