Neuron-Level Differentiation of Memorization and Generalization in Large Language Models
National Taiwan University · Department of computer science and informational engineering, National Taiwan University · and informational engineering, National Taiwan University · National Tsinghua University and Google · National Taiwan University and National Taiwan University
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。DOI 10.18653/v1/2025.emnlp-main.812 ↗
摘要
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.