@inproceedings{zeng-etal-2024-exploring,
    title = "Exploring Memorization in Fine-tuned Language Models",
    author = "Zeng, Shenglai  and
      Li, Yaxin  and
      Ren, Jie  and
      Liu, Yiding  and
      Xu, Han  and
      He, Pengfei  and
      Xing, Yue  and
      Wang, Shuaiqiang  and
      Tang, Jiliang  and
      Yin, Dawei",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.acl-long.216/",
    doi = "10.18653/v1/2024.acl-long.216",
    pages = "3917--3948",
    abstract = "Large language models (LLMs) have shown great capabilities in various tasks but also exhibited memorization of training data, raising tremendous privacy and copyright concerns. While prior works have studied memorization during pre-training, the exploration of memorization during fine-tuning is rather limited. Compared to pre-training, fine-tuning typically involves more sensitive data and diverse objectives, thus may bring distinct privacy risks and unique memorization behaviors. In this work, we conduct the first comprehensive analysis to explore language models' (LMs) memorization during fine-tuning across tasks. Our studies with open-sourced and our own fine-tuned LMs across various tasks indicate that memorization presents a strong disparity among different fine-tuning tasks. We provide an intuitive explanation of this task disparity via sparse coding theory and unveil a strong correlation between memorization and attention score distribution."
}