Automated Program Repair: Emerging Trends Pose and Expose Problems for Benchmarks

Abstract

Machine learning (ML) pervades the field of Automated Program Repair (APR). Algorithms deploy neural machine translation and large language models (LLMs) to generate software patches, among other tasks. But, there are important differences between these applications of ML and earlier work, which complicates the task of ensuring that results are valid and likely to generalize. A challenge is that the most popular APR evaluation benchmarks were not designed with ML techniques in mind. This is especially true for LLMs, whose large and often poorly-disclosed training datasets may include problems on which they are evaluated. This paper reviews work in APR published in the field’s top five venues since 2018, emphasizing emerging trends in the field, including the dramatic rise of ML models, including LLMs. ML-based papers are categorized along structural and functional dimensions, and a variety of issues are identified that these new methods raise. Importantly, data leakage and contamination concerns arise from the challenge of validating ML-based APR using existing benchmarks, which were designed before these techniques were popular. We discuss inconsistencies in evaluation design and performance reporting and offer pointers to solutions where they are available. Finally, we highlight promising new directions that the field is already taking.