Think or Remember? Detecting and Directing LLMs Towards Memorization or Generalization
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.
Code (0)
등록된 구현이 없습니다.
Tasks
MemorizationSimilar Papers 제목 키워드 기반
Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries
Evaluations of unlearning on reasoning models sometimes show a bypass pattern. The answer side looks unlearned, but the model's own thinking trace keeps emitting the forgotten content, and the gap is taken as evidence th…
Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces
Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also ``think in space''…
Question AnsweringSpatial ReasoningMemorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis
While Large Language Models (LLMs) achieve remarkable performance through training on massive datasets, they can exhibit concerning behaviors such as verbatim reproduction of training data rather than true generalization…
ArticlesHumanEvalMemorizationRethinking Memorization Measures and their Implications in Large Language Models
Concerned with privacy threats, memorization in LLMs is often seen as undesirable, specifically for learning. In this paper, we study whether memorization can be avoided when optimally learning a language, and whether th…
Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching
Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Current routing methods primarily rely on direct mapping from queries to …