@inproceedings{huang-etal-2025-neuron,
    title = "Neuron-Level Differentiation of Memorization and Generalization in Large Language Models",
    author = "Huang, Ko-Wei  and
      Fu, Yi-Fu  and
      Tsai, Ching-Yu  and
      Tu, Yu-Chieh  and
      Cheng, Tzu-ling  and
      Lin, Cheng-Yu  and
      Yang, Yi-Ting  and
      Liu, Heng-Yi  and
      Liao, Keng-Te  and
      Juan, Da-Cheng  and
      Lin, Shou-De",
    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/ingest-emnlp/2025.emnlp-main.812/",
    pages = "16077--16091",
    ISBN = "979-8-89176-332-6",
    abstract = "We investigate how Large Language Models (LLMs) distinguish between memorization and generalization at the neuron level. Through carefully designed tasks, we identify distinct neuron subsets responsible for each behavior. Experiments on both a GPT-2 model trained from scratch and a pretrained LLaMA-3.2 model fine-tuned with LoRA show consistent neuron-level specialization. We further demonstrate that inference-time interventions on these neurons can steer the model{'}s behavior toward memorization or generalization. To assess robustness, we evaluate intra-task and inter-task consistency, confirming that these neuron-behavior associations reflect generalizable patterns rather than dataset-specific artifacts. Our findings reveal modular structure in LLMs and enable controlling memorization and generalization behaviors at inference time."
}