Guardado en:
Detalles Bibliográficos
Autores principales: Pan, Xu, Hahami, Ely, Zhang, Zechen, Sompolinsky, Haim
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2504.21239
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910922678730752
author Pan, Xu
Hahami, Ely
Zhang, Zechen
Sompolinsky, Haim
author_facet Pan, Xu
Hahami, Ely
Zhang, Zechen
Sompolinsky, Haim
contents Large Language Models (LLMs) currently struggle to sequentially add new memories and integrate new knowledge. These limitations contrast with the human ability to continuously learn from new experiences and acquire knowledge throughout life. Most existing approaches add memories either through large context windows or external memory buffers (e.g., Retrieval-Augmented Generation), and studies on knowledge injection rarely test scenarios resembling everyday life events. In this work, we introduce a continual learning framework, Memory Embedded in Gated LLMs (MEGa), which injects event memories directly into the weights of LLMs. Each memory is stored in a dedicated set of gated low-rank weights. During inference, a gating mechanism activates relevant memory weights by matching query embeddings to stored memory embeddings. This enables the model to both recall entire memories and answer related questions. On two datasets - fictional characters and Wikipedia events - MEGa outperforms baseline approaches in mitigating catastrophic forgetting. Our model draws inspiration from the complementary memory system of the human brain.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21239
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Memorization and Knowledge Injection in Gated LLMs
Pan, Xu
Hahami, Ely
Zhang, Zechen
Sompolinsky, Haim
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) currently struggle to sequentially add new memories and integrate new knowledge. These limitations contrast with the human ability to continuously learn from new experiences and acquire knowledge throughout life. Most existing approaches add memories either through large context windows or external memory buffers (e.g., Retrieval-Augmented Generation), and studies on knowledge injection rarely test scenarios resembling everyday life events. In this work, we introduce a continual learning framework, Memory Embedded in Gated LLMs (MEGa), which injects event memories directly into the weights of LLMs. Each memory is stored in a dedicated set of gated low-rank weights. During inference, a gating mechanism activates relevant memory weights by matching query embeddings to stored memory embeddings. This enables the model to both recall entire memories and answer related questions. On two datasets - fictional characters and Wikipedia events - MEGa outperforms baseline approaches in mitigating catastrophic forgetting. Our model draws inspiration from the complementary memory system of the human brain.
title Memorization and Knowledge Injection in Gated LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2504.21239