@inproceedings{pan-etal-2025-alinfik,
    title = "{AL}in{F}i{K}: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Parity {LLM} Data Valuation",
    author = "Pan, Yanzhou  and
      Lin, Huawei  and
      Ran, Yide  and
      Chen, Jiamin  and
      Yu, Xiaodong  and
      Zhao, Weijie  and
      Zhang, Denghui  and
      Xu, Zhaozhuo",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.589/",
    pages = "11756--11771",
    ISBN = "979-8-89176-189-6",
    abstract = "Large Language Models (LLMs) heavily rely on high-quality training data, making data valuation crucial for optimizing model performance, especially when working within a limited budget. In this work, we aim to offer a third-party data valuation approach that benefits both data providers and model developers. We introduce a linearized future influence kernel (LinFiK), which assesses the value of individual data samples in improving LLM performance during training. We further propose ALinFiK, a learning strategy to approximate LinFiK, enabling scalable data valuation. Our comprehensive evaluations demonstrate that this approach surpasses existing baselines in effectiveness and efficiency, demonstrating significant scalability advantages as LLM parameters increase."
}