Think or Remember? Detecting and Directing LLMs Towards Memorization or Generalization

• URL: http://arxiv.org/abs/2412.18497v1
• Date: Tue, 24 Dec 2024 15:28:56 GMT
• Title: Think or Remember? Detecting and Directing LLMs Towards Memorization or Generalization
• Authors: Yi-Fu Fu, Yu-Chieh Tu, Tzu-Ling Cheng, Cheng-Yu Lin, Yi-Ting Yang, Heng-Yi Liu, Keng-Te Liao, Da-Cheng Juan, Shou-De Lin,
• Abstract summary: We explore the foundational mechanisms of memorization and generalization in Large Language Models (LLMs)<n>Our investigation serves as a case study leveraging specially designed datasets and experimental-scale LLMs.
• Score: 10.11351265687309
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we explore the foundational mechanisms of memorization and generalization in Large Language Models (LLMs), inspired by the functional specialization observed in the human brain. Our investigation serves as a case study leveraging specially designed datasets and experimental-scale LLMs to lay the groundwork for understanding these behaviors. Specifically, we aim to first enable LLMs to exhibit both memorization and generalization by training with the designed dataset, then (a) examine whether LLMs exhibit neuron-level spatial differentiation for memorization and generalization, (b) predict these behaviors using model internal representations, and (c) steer the behaviors through inference-time interventions. Our findings reveal that neuron-wise differentiation of memorization and generalization is observable in LLMs, and targeted interventions can successfully direct their behavior.

Related papers

• Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning [22.627302782393865]
  This paper investigates the relationship between large language models' (LLMs) ability to recognize repetitive input patterns and their performance on in-context learning (ICL)<n>Our experiments reveal that the impact of repetition neurons on ICL performance varies depending on the depth of the layer in which they reside.
  arXiv  Detail & Related papers  (2025-07-10T14:40:31Z)
• A Call for New Recipes to Enhance Spatial Reasoning in MLLMs [85.67171333213301]
  Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks. Recent studies have exposed critical limitations in their spatial reasoning capabilities. This deficiency in spatial reasoning significantly constrains MLLMs' ability to interact effectively with the physical world.
  arXiv  Detail & Related papers  (2025-04-21T11:48:39Z)
• Multimodal LLM Augmented Reasoning for Interpretable Visual Perception Analysis [19.032828729570458]
  We use established principles and explanations from psychology and cognitive science related to complexity in human visual perception. Our study aims to benchmark MLLMs across various explainability principles relevant to visual perception.
  arXiv  Detail & Related papers  (2025-04-16T22:14:27Z)
• The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction [34.86855316803838]
  We identify a set of linear features in the model's residual stream that govern the balance between genuine reasoning and memory recall. We show that intervening in these reasoning features helps the model more accurately activate the most relevant problem-solving capabilities during answer generation.
  arXiv  Detail & Related papers  (2025-03-29T14:00:44Z)
• Analyzing Memorization in Large Language Models through the Lens of Model Attribution [11.295483963637217]
  Large Language Models (LLMs) are prevalent in modern applications but often memorize training data, leading to privacy breaches and copyright issues. We investigate memorization from an architectural lens by analyzing how attention modules at different layers impact its memorization and generalization.
  arXiv  Detail & Related papers  (2025-01-09T09:00:32Z)
• Detecting Memorization in Large Language Models [0.0]
  Large language models (LLMs) have achieved impressive results in natural language processing but are prone to memorizing portions of their training data.<n>Traditional methods for detecting memorization rely on output probabilities or loss functions.<n>We introduce an analytical method that precisely detects memorization by examining neuron activations within the LLM.
  arXiv  Detail & Related papers  (2024-12-02T00:17:43Z)
• Generative forecasting of brain activity enhances Alzheimer's classification and interpretation [16.09844316281377]
  Resting-state functional magnetic resonance imaging (rs-fMRI) offers a non-invasive method to monitor neural activity. Deep learning has shown promise in capturing these representations. In this study, we focus on time series forecasting of independent component networks derived from rs-fMRI as a form of data augmentation.
  arXiv  Detail & Related papers  (2024-10-30T23:51:31Z)
• Brain-like Functional Organization within Large Language Models [58.93629121400745]
  The human brain has long inspired the pursuit of artificial intelligence (AI) Recent neuroimaging studies provide compelling evidence of alignment between the computational representation of artificial neural networks (ANNs) and the neural responses of the human brain to stimuli. In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs) This framework links the AN sub-groups to FBNs, enabling the delineation of brain-like functional organization within large language models (LLMs)
  arXiv  Detail & Related papers  (2024-10-25T13:15:17Z)
• Mind Scramble: Unveiling Large Language Model Psychology Via Typoglycemia [27.650551131885152]
  Research into large language models (LLMs) has shown promise in addressing complex tasks in the physical world. Studies suggest that powerful LLMs, like GPT-4, are beginning to exhibit human-like cognitive abilities.
  arXiv  Detail & Related papers  (2024-10-02T15:47:25Z)
• Modularity in Transformers: Investigating Neuron Separability & Specialization [0.0]
  Transformer models are increasingly prevalent in various applications, yet our understanding of their internal workings remains limited. This paper investigates the modularity and task specialization of neurons within transformer architectures, focusing on both vision (ViT) and language (Mistral 7B) models. Using a combination of selective pruning and MoEfication clustering techniques, we analyze the overlap and specialization of neurons across different tasks and data subsets.
  arXiv  Detail & Related papers  (2024-08-30T14:35:01Z)
• Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making [51.737762570776006]
  LLM-ACTR is a novel neuro-symbolic architecture that provides human-aligned and versatile decision-making. Our framework extracts and embeds knowledge of ACT-R's internal decision-making process as latent neural representations. Our experiments on novel Design for Manufacturing tasks show both improved task performance as well as improved grounded decision-making capability.
  arXiv  Detail & Related papers  (2024-08-17T11:49:53Z)
• Analysis of Argument Structure Constructions in a Deep Recurrent Language Model [0.0]
  We explore the representation and processing of Argument Structure Constructions (ASCs) in a recurrent neural language model. Our results show that sentence representations form distinct clusters corresponding to the four ASCs across all hidden layers. This indicates that even a relatively simple, brain-constrained recurrent neural network can effectively differentiate between various construction types.
  arXiv  Detail & Related papers  (2024-08-06T09:27:41Z)
• Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data [76.90128359866462]
  We introduce an extended concept of memorization, distributional memorization, which measures the correlation between the output probabilities and the pretraining data frequency.<n>We show that memorization plays a larger role in simpler, knowledge-intensive tasks, while generalization is the key for harder, reasoning-based tasks.
  arXiv  Detail & Related papers  (2024-07-20T21:24:40Z)
• Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation [56.34634121544929]
  In this study, we first construct the brain-effective network via the dynamic causal model. We then introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE) This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks.
  arXiv  Detail & Related papers  (2024-05-21T20:37:07Z)
• MindBridge: A Cross-Subject Brain Decoding Framework [60.58552697067837]
  Brain decoding aims to reconstruct stimuli from acquired brain signals. Currently, brain decoding is confined to a per-subject-per-model paradigm. We present MindBridge, that achieves cross-subject brain decoding by employing only one model.
  arXiv  Detail & Related papers  (2024-04-11T15:46:42Z)
• Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension [63.330262740414646]
  We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs) We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
  arXiv  Detail & Related papers  (2024-02-28T04:56:21Z)
• Exploring the Cognitive Knowledge Structure of Large Language Models: An Educational Diagnostic Assessment Approach [50.125704610228254]
  Large Language Models (LLMs) have not only exhibited exceptional performance across various tasks, but also demonstrated sparks of intelligence. Recent studies have focused on assessing their capabilities on human exams and revealed their impressive competence in different domains. We conduct an evaluation using MoocRadar, a meticulously annotated human test dataset based on Bloom taxonomy.
  arXiv  Detail & Related papers  (2023-10-12T09:55:45Z)
• Exploring Memorization in Fine-tuned Language Models [53.52403444655213]
  We conduct the first comprehensive analysis to explore language models' memorization during fine-tuning across tasks. Our studies with open-sourced and our own fine-tuned LMs across various tasks indicate that memorization presents a strong disparity among different fine-tuning tasks. We provide an intuitive explanation of this task disparity via sparse coding theory and unveil a strong correlation between memorization and attention score distribution.
  arXiv  Detail & Related papers  (2023-10-10T15:41:26Z)
• Probing Large Language Models from A Human Behavioral Perspective [24.109080140701188]
  Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP. The understanding of their prediction processes and internal mechanisms, such as feed-forward networks (FFN) and multi-head self-attention (MHSA) remains largely unexplored.
  arXiv  Detail & Related papers  (2023-10-08T16:16:21Z)
• An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning [70.48605869773814]
  Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information. This study empirically evaluates the forgetting phenomenon in large language models during continual instruction tuning.
  arXiv  Detail & Related papers  (2023-08-17T02:53:23Z)
• Measures of Information Reflect Memorization Patterns [53.71420125627608]
  We show that the diversity in the activation patterns of different neurons is reflective of model generalization and memorization. Importantly, we discover that information organization points to the two forms of memorization, even for neural activations computed on unlabelled in-distribution examples.
  arXiv  Detail & Related papers  (2022-10-17T20:15:24Z)
• On the Evolution of Neuron Communities in a Deep Learning Architecture [0.7106986689736827]
  This paper examines the neuron activation patterns of deep learning-based classification models. We show that both the community quality (modularity) and entropy are closely related to the deep learning models' performances.
  arXiv  Detail & Related papers  (2021-06-08T21:09:55Z)
• Compositional Explanations of Neurons [52.71742655312625]
  We describe a procedure for explaining neurons in deep representations by identifying compositional logical concepts. We use this procedure to answer several questions on interpretability in models for vision and natural language processing.
  arXiv  Detail & Related papers  (2020-06-24T20:37:05Z)
• Compositional Generalization by Learning Analytical Expressions [87.15737632096378]
  A memory-augmented neural model is connected with analytical expressions to achieve compositional generalization. Experiments on the well-known benchmark SCAN demonstrate that our model seizes a great ability of compositional generalization.
  arXiv  Detail & Related papers  (2020-06-18T15:50:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.