@inproceedings{lv-etal-2025-inject,
    title = "How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models",
    author = "Lv, Kangtao  and
      Chen, Haibin  and
      Yuan, Yujin  and
      Liu, Langming  and
      Liu, Shilei  and
      Wang, Yongwei  and
      Su, Wenbo  and
      Zheng, Bo",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-11/2025.emnlp-main.1331/",
    doi = "10.18653/v1/2025.emnlp-main.1331",
    pages = "26204--26219",
    ISBN = "979-8-89176-332-6",
    abstract = "Large language models (LLMs) have attracted significant attention due to their impressive general capabilities across diverse downstream tasks. However, without domain-specific optimization, they often underperform on specialized knowledge benchmarks and even produce hallucination. Recent studies show that strategically infusing domain knowledge during pretraining can substantially improve downstream performance. A critical challenge lies in balancing this infusion trade-off: injecting too little domain-specific data yields insufficient specialization, whereas excessive infusion triggers catastrophic forgetting of previously acquired knowledge. In this work, we focus on the phenomenon of memory collapse induced by over-infusion. Through systematic experiments, we make two key observations, i.e. 1) Critical collapse point: each model exhibits a threshold beyond which its knowledge retention capabilities sharply degrade. 2) Scale correlation: these collapse points scale consistently with the model{'}s size. Building on these insights, we propose a knowledge infusion scaling law that predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts. Extensive experiments across different model sizes and pertaining token budgets validate both the effectiveness and generalizability of our scaling law."
}