@inproceedings{zhang-etal-2025-turning,
    title = "Turning the Tide: Repository-based Code Reflection",
    author = "Zhang, Wei  and
      Yang, Jian  and
      Yang, Jiaxi  and
      Wang, Ya  and
      Li, Zhoujun  and
      Cui, Zeyu  and
      Hui, Binyuan  and
      Lin, Junyang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.377/",
    doi = "10.18653/v1/2025.findings-emnlp.377",
    pages = "7148--7164",
    ISBN = "979-8-89176-335-7",
    abstract = "Code large language models (LLMs) enhance programming by understanding and generating code across languages, offering intelligent feedback, bug detection, and code updates through reflection, improving development efficiency and accessibility. While benchmarks (e.g. HumanEval/LiveCodeBench) evaluate code generation and real-world relevance, previous works ignores the scenario of modifying code in repositories. Considering challenges remaining in improving reflection capabilities and avoiding data contamination in dynamic benchmarks, we introduce , a challenging benchmark for evaluating code understanding and generation in multi-file repository contexts, featuring 1,888 rigorously filtered test cases across 6 programming languages to ensure diversity, correctness, and high difficulty. Further, we create , a large-scale, quality-filtered instruction-tuning dataset derived from diverse sources, used to train through a two-turn dialogue process involving code generation and error-driven repair. The leaderboard evaluates over 40 LLMs to reflect the model performance of repository-based code reflection."
}