{"paper":{"title":"Empirical Evaluation of Large Language Models in Automated Program Repair","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fengjie Li, Hongyu Zhang, Jiajun Jiang, Jiajun Sun, Xinzhu Qi","submitted_at":"2025-06-16T07:52:15Z","abstract_excerpt":"The increasing prevalence of software bugs has made automated program repair (APR) a key research focus. Large language models (LLMs) offer new opportunities for APR, but existing studies mostly rely on smaller, earlier-generation models and Java benchmarks. The repair capabilities of modern, large-scale LLMs across diverse languages and scenarios remain underexplored. To address this, we conduct a comprehensive empirical study of four open-source LLMs, CodeLlama, LLaMA, StarCoder, and DeepSeek-Coder, spanning 7B to 33B parameters, diverse architectures, and purposes. We evaluate them across t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13186","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.13186/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}