RET-LLM: Towards a General Read-Write Memory for Large Language Models

MCML Authors

Ali Modarressi

→ Group Hinrich Schütze
 Computational Linguistics

Ayyoob Imani

→ Group Hinrich Schütze
 Computational Linguistics

Hinrich Schütze

Prof. Dr.

Principal Investigator

Computational Linguistics

Abstract

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.

inproceedings

---

AGI @ICLR 2024

Workshop on Artificial General Intelligence at the 12th International Conference on Learning Representations. Vienna, Austria, May 07-11, 2024.

---

Authors

A. Modarressi • A. Imani • M. Fayyaz • H. Schütze

---

Links

---

Research Area

 B2 | Natural Language Processing