Large language models (LLMs) have significantly advanced the field of natural
language processing (NLP) through their extensive parameters and comprehensive
data utilization. However, existing LLMs lack a dedicated memory unit, limiting
their ability to explicitly store and retrieve knowledge for various tasks. In
this paper, we propose RET-LLM a novel framework that equips LLMs with a
general write-read memory unit, allowing them to extract, store, and recall
knowledge from the text as needed for task performance. Inspired by Davidsonian
semantics theory, we extract and save knowledge in the form of triplets. The
memory unit is designed to be scalable, aggregatable, updatable, and
interpretable. Through qualitative evaluations, we demonstrate the superiority
of our proposed framework over baseline approaches in question answering tasks.
Moreover, our framework exhibits robust performance in handling temporal-based
question answering tasks, showcasing its ability to effectively manage
time-dependent information.

提出了一种新的 RET-LLM 框架，它为 LLMs 提供了一个通用的写 - 读内存单元，使它们能够从文本中提取、存储和检索知识，以便进行任务执行。通过 Davidsonian 语义理论，以三元组的形式提取和保存知识，在问答任务中展现出比基线方法更卓越的性能。此外，该框架在处理基于时间的问题回答任务时表现出了强大的性能，展示了它有效处理时态信息的能力。