Neuron-Level Differentiation of Memorization and Generalization in Large Language Models
This work addresses the problem of understanding and controlling memorization vs. generalization in LLMs for researchers and practitioners, though it is incremental as it builds on existing neuron-level analysis methods.
The study identified distinct neuron subsets in large language models responsible for memorization and generalization, showing that inference-time interventions on these neurons can steer model behavior, with consistent results across GPT-2 and LLaMA-3.2 models.
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.