一句话：针对大型代码模型微调中标签噪声未被充分探索的问题，提出先过滤噪声标签再微调的鲁棒微调思路。
论文关注大型代码模型（LCMs）在软件工程任务微调时对高质量标注数据的依赖问题。实际数据常含噪声标签，会显著损害微调后模型的泛化能力和整体性能。已有工作主要研究从零开始训练模型时的标签噪声，而 LCM 微调场景下的噪声标签问题仍缺乏探索。标题表明论文提出“先过滤再微调”的策略，即在微调前对训练样本进行噪声标签过滤，以提升噪声标签下微调的鲁棒性。摘要未报告具体过滤方法、基准任务与量化结果，因此其实证效果和适用边界有待正文验证。
Fine-tuning plays a crucial role in adapting large code models (LCMs) to specific software engineering tasks. However, fine-tuning LCMs requires perfectly labeled datasets, which are rarely available in practice. Noisy labels in the training data can significantly impair the generalization ability and overall performance of fine-tuned LCMs. Previous work has primarily focused on the problem of noisy labels in training models from scratch, while this problem remains largely unexplored in the context of fine-tuning LCMs.
@inproceedings{paperbot11854,
title = {Filtering before Tuning: Robust Fine-Tuning of Large Code Models under Noisy Labels},
author = {Zhong Li and Yang Chen and Heng Yong and Yuanyi Lin and Jiali Zhao and Tongtong Xu and Minxue Pan and Tian Zhang and Xuandong Li},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787785}
}