@inproceedings{wen-etal-2024-sibo,
    title = "{SIBO}: A Simple Booster for Parameter-Efficient Fine-Tuning",
    author = "Wen, Zhihao  and
      Zhang, Jie  and
      Fang, Yuan",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.findings-acl.72/",
    doi = "10.18653/v1/2024.findings-acl.72",
    pages = "1241--1257",
    abstract = "Fine-tuning all parameters of large language models (LLMs) necessitates substantial computational power and extended time. Latest advancements in parameter-efficient fine-tuning (PEFT) techniques, such as Adapter tuning and LoRA, allow for adjustments to only a minor fraction of the parameters of these LLMs. Concurrently, it has been noted that the issue of over-smoothing diminishes the effectiveness of these Transformer-based LLMs, resulting in suboptimal performances in downstream tasks. In this paper, we present SIBO, which is a SImple BOoster to enhance PEFT, by injecting an initial residual. SIBO is straightforward and readily extensible to a range of state-of-the-art PEFT techniques to alleviate over-smoothing and enhance performance. Extensive experiments on 22 benchmark datasets demonstrate that SIBO significantly enhances the performance of various strong baselines, achieving up to 15.7{\%} and 23.5{\%} improvement over existing PEFT methods on the arithmetic and commonsense reasoning tasks, respectively."
}