$\text{Memory}^3$: Language Modeling with Explicit Memory
- URL: http://arxiv.org/abs/2407.01178v1
- Date: Mon, 1 Jul 2024 11:07:23 GMT
- Title: $\text{Memory}^3$: Language Modeling with Explicit Memory
- Authors: Hongkang Yang, Zehao Lin, Wenjin Wang, Hao Wu, Zhiyu Li, Bo Tang, Wenqiang Wei, Jinbo Wang, Zeyun Tang, Shichao Song, Chenyang Xi, Yu Yu, Kai Chen, Feiyu Xiong, Linpeng Tang, Weinan E,
- Abstract summary: We equip large language models (LLMs) with explicit memory, a memory format cheaper than model parameters and text retrieval-augmented generation (RAG)
As a preliminary proof of concept, we train from scratch a 2.4B LLM, which achieves better performance than much larger LLMs and RAG models.
We introduce a memory circuitry theory to support the externalization of knowledge, and present novel techniques including a memory sparsification mechanism that makes storage tractable.
- Score: 22.572376536612015
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The training and inference of large language models (LLMs) are together a costly process that transports knowledge from raw data to meaningful computation. Inspired by the memory hierarchy of the human brain, we reduce this cost by equipping LLMs with explicit memory, a memory format cheaper than model parameters and text retrieval-augmented generation (RAG). Conceptually, with most of its knowledge externalized to explicit memories, the LLM can enjoy a smaller parameter size, training cost, and inference cost, all proportional to the amount of remaining "abstract knowledge". As a preliminary proof of concept, we train from scratch a 2.4B LLM, which achieves better performance than much larger LLMs as well as RAG models, and maintains higher decoding speed than RAG. The model is named $\text{Memory}^3$, since explicit memory is the third form of memory in LLMs after implicit memory (model parameters) and working memory (context key-values). We introduce a memory circuitry theory to support the externalization of knowledge, and present novel techniques including a memory sparsification mechanism that makes storage tractable and a two-stage pretraining scheme that facilitates memory formation.
Related papers
- Memory Layers at Scale [67.00854080570979]
This work takes memory layers beyond proof-of-concept, proving their utility at contemporary scale.
On downstream tasks, language models augmented with our improved memory layer outperform dense models with more than twice the budget, as well as mixture-of-expert models when matched for both compute and parameters.
We provide a fully parallelizable memory layer implementation, demonstrating scaling laws with up to 128B memory parameters, pretrained to 1 trillion tokens, comparing to base models with up to 8B parameters.
arXiv Detail & Related papers (2024-12-12T23:56:57Z) - MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training [24.066283519769968]
Large Language Models (LLMs) have been trained using extended context lengths to foster more creative applications.
We propose MEMO, a novel framework for fine-grained activation memory management.
MeMO achieves an average of 1.97x and 1.80x MFU compared to Megatron-LM and DeepSpeed.
arXiv Detail & Related papers (2024-07-16T18:59:49Z) - HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing [33.720656946186885]
Hierarchical Memory Transformer (HMT) is a novel framework that facilitates a model's long-context processing ability.
HMT consistently improves the long-context processing ability of existing models.
arXiv Detail & Related papers (2024-05-09T19:32:49Z) - MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory [49.96019697955383]
We introduce MemLLM, a novel method of enhancing large language models (LLMs) by integrating a structured and explicit read-and-write memory module.
Our experiments indicate that MemLLM enhances the LLM's performance and interpretability, in language modeling in general and knowledge-intensive tasks in particular.
arXiv Detail & Related papers (2024-04-17T18:13:16Z) - In-context Autoencoder for Context Compression in a Large Language Model [70.7621953091318]
We propose the In-context Autoencoder (ICAE) to compress a long context into short compact memory slots.
ICAE is first pretrained using both autoencoding and language modeling objectives on massive text data.
arXiv Detail & Related papers (2023-07-13T17:59:21Z) - GLIMMER: generalized late-interaction memory reranker [29.434777627686692]
Memory-augmentation is a powerful approach for incorporating external information into language models.
Recent work introduced LUMEN, a memory-retrieval hybrid that partially pre-computes memory and updates memory representations on the fly with a smaller live encoder.
We propose GLIMMER, which improves on this approach through 1) exploiting free access to the powerful memory representations by applying a shallow reranker on top of memory to drastically improve retrieval quality at low cost.
arXiv Detail & Related papers (2023-06-17T01:54:25Z) - Augmenting Language Models with Long-Term Memory [142.04940250657637]
Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit.
We propose a framework, Language Models Augmented with Long-Term Memory (LongMem), which enables LLMs to memorize long history.
arXiv Detail & Related papers (2023-06-12T15:13:39Z) - RET-LLM: Towards a General Read-Write Memory for Large Language Models [53.288356721954514]
RET-LLM is a novel framework that equips large language models with a general write-read memory unit.
Inspired by Davidsonian semantics theory, we extract and save knowledge in the form of triplets.
Our framework exhibits robust performance in handling temporal-based question answering tasks.
arXiv Detail & Related papers (2023-05-23T17:53:38Z) - A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental
Learning [56.450090618578]
Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement.
We show that when counting the model size into the total budget and comparing methods with aligned memory size, saving models do not consistently work.
We propose a simple yet effective baseline, denoted as MEMO for Memory-efficient Expandable MOdel.
arXiv Detail & Related papers (2022-05-26T08:24:01Z)
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.