More sizzle than steak? Using an LLM to produce verified bug fixes (new preprint)
New article: “Do AI models help produce verified bug fixes?” (Huang Li, Ilgiz Mustafin, Marco Piccioni, Alessandro Schena, Reto Weber and Bertrand Meyer), submitted for publication, preprint available on arXiv. Automatic Program Repair (APR) involves four steps: Locating the bug. Producing candidate corrections. Validating them (to make sure that they do correct the problem). Selecting the … Read more