EUVIMEDEUVIMED entdecken
Crossref

MORepair : Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning

Boyang Yang, Haoye Tian, Jiadong Ren, Hongyu Zhang, Jacques Klein, Tegawendé F. Bissyandé, Claire Le Goues, Shunfu Jin

ACM Transactions on Software Engineering and Methodology · 28.02.2026 · 35 (2) · 1-38

DOI: 10.1145/3735129 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 21.01.2026. Verfasst von Boyang Yang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation, Central Leading Local Science and Technology Development Project of Hebei Province, Innovation Capability Improvement Plan Project of Hebei Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models (LLMs) to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks generally overlook the need to reason about the logic behind code changes, beyond syntactic patterns in the data. High-performing fine-tuning experiments also usually come at very high computational costs. With MORepair , we propose a novel perspective on the learning focus of LLM fine-tuning for program repair: we not only adapt the LLM parameters to the syntactic nuances of the task of code transformation (objective ➊), but we also specifically fine-tune the LLM with respect to the logical reason behind the code change in the training data (objective ➋). Such a multi-objective fine-tuning will instruct LLMs to generate high-quality patches. We apply MORepair to fine-tune four open-source LLMs with different sizes and architectures. Experimental results on function-level and repository-level repair benchmarks show that the implemented fine-tuning effectively boosts LLM repair performance by 11.4% to 56.0%. We further show that our fine-tuning strategy yields superior performance compared to the state-of-the-art approaches, including standard fine-tuning, Fine-tune-CoT, and RepairLLaMA.

Förderung

  • National Natural Science Foundation
  • Central Leading Local Science and Technology Development Project of Hebei Province
  • Innovation Capability Improvement Plan Project of Hebei Province
  • European Research Council under the European Union’s Horizon 2020 research and innovation program
  • Australian Research Council Discovery Project
  • Beijing JudaoYouda Network Technology Limited Company

Zitieren

APA

Yang, B., Tian, H., Ren, J., Zhang, H., Klein, J., Bissyandé, T. F., Goues, C. L., & Jin, S. (2026). MORepair : Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning. ACM Transactions on Software Engineering and Methodology, 35(2), 1-38. https://doi.org/10.1145/3735129

Vancouver

Yang B, Tian H, Ren J, Zhang H, Klein J, Bissyandé TF, et al. MORepair : Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning. ACM Transactions on Software Engineering and Methodology. 2026;35(2):1-38. doi:10.1145/3735129

BibTeX
@article{Yang2026,
  author = {Yang, Boyang and Tian, Haoye and Ren, Jiadong and Zhang, Hongyu and Klein, Jacques and Bissyandé, Tegawendé F. and Goues, Claire Le and Jin, Shunfu},
  title = {MORepair : Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  volume = {35},
  number = {2},
  pages = {1--38},
  doi = {10.1145/3735129}
}
Kostenlos starten →