Neuron-Level Differentiation of Memorization and Generalization in Large Language Models
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 25 references that are in the map. First posted on arXiv 24 Dec 2024.
Builds on
16 of 25 references.
References · 16
- 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
- 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
- 2021Deduplicating Training Data Makes Language Models Bettercited by 714
- 2015Towards AI-Complete Question Answering: A Set of Prerequisite Toy Taskscited by 314
- 2024Programming Refusal with Conditional Activation Steeringcited by 206
- 2023Can LLM-Generated Misinformation Be Detected?cited by 177
- 2024Improving Instruction-Following in Language Models through Activation Steeringcited by 160
- 2024Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimizationcited by 118
- 2024On Memorization of Large Language Models in Logical Reasoningcited by 117
- 2024Rethinking LLM Memorization through the Lens of Adversarial Compressioncited by 94
- 2021Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluationcited by 70
- 2024Demystifying Verbatim Memorization in Large Language Modelscited by 56
4 more
- 2024Can LLM Graph Reasoning Generalize beyond Pattern Memorization?cited by 47
- 2024Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distributioncited by 27
- 2024Steering Large Language Models between Code Execution and Textual Reasoningcited by 24
- 2024Quantifying In-Context Reasoning Effects and Memorization Effects in LLMscited by 3
Built on by
Citing papers per year: 2025: 2.
2 papers.