MeMo: Memory as a Model

Ryan Wei Heng Quek, Sanghyuk Lee, Alfred Wei Lun Leong, Arun Verma, Alok Prakash, Nancy F. Chen, Bryan Kian Hsiang Low, Daniela Rus, Armando Solar-Lezama

Keywords: Large Language Models, Knowledge Augmentation, Retrieval-Augmented Generation, Catastrophic Forgetting, Latent Memory Models

TL;DR: This paper introduces MeMo, a framework that augments any LLM with up-to-date or domain-specific knowledge via a trained memory model, avoiding costly retraining, mitigating catastrophic forgetting, and remaining robust to retrieval noise.

Abstract: Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications require timely, domain-specific information, motivating the need for efficient mechanisms to incorporate new knowledge. In this paper, we introduce MeMo (Memory as a Model), a modular framework that encodes new knowledge into a dedicated Memory model while keeping the LLM unchanged. Compared to existing methods, MeMo offers several advantages: (a) it captures complex cross-document relationships, (b) it is robust to retrieval noise, (c) it avoids catastrophic forgetting in the LLM, (d) it does not require access to the LLM’s weights or output logits that enabling plug-and-play integration with both open and proprietary LLMs, and (e) its retrieval cost is independent of corpus size at inference time. Our experiments on three benchmarks, BrowseComp-Plus, NarrativeQA, and MuSiQue, show that MeMo achieves strong performance compared to existing methods across diverse settings.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 91