Echo: A Large Language Model with Temporal Episodic Memory

TL;DR

This paper introduces Echo, a large language model enhanced with temporal episodic memory, and a new benchmark to evaluate its memory capabilities, demonstrating significant improvements over existing models in episodic memory tasks.

Contribution

We propose a novel training framework and benchmark for episodic memory in large language models, enabling better handling of complex, multi-turn memory-based queries.

Findings

Echo outperforms state-of-the-art LLMs on EM-Test.

The model exhibits human-like episodic memory capabilities.

The framework effectively incorporates temporal information into training.

Abstract

Research on large language models (LLMs) has shown remarkable performance in domains such as mathematics, programming, and literary creation. However, most studies have focused on semantic memory-based question answering, neglecting LLMs' potential to handle episodic memory (EM)-related queries. This oversight has led to suboptimal performance in applications requiring EM, including emotional companionship, personal AI assistants, and AI teachers. To address this gap, we introduce Echo, a LLM enhanced with temporal episodic memory. We propose a Multi-Agent Data Generation Framework that guides the model in generating multi-turn, complex scenario episodic memory dialogue data (EM-Train). Temporal information is innovatively incorporated into the LLM training process, and Echo is trained using the EM-Train. Furthermore, We develop an EM-Test benchmark specifically designed to evaluate LLMs' episodic memory capabilities. The EM-Test assesses performance across various time spans and difficulty levels, providing a comprehensive evaluation of multi-turn episodic memory dialogues. Our experiments demonstrate that Echo significantly outperforms state-of-the-art LLMs on EM-Test. Additionally, a qualitative analysis reveals Echo's potential to exhibit human-like episodic memory capabilities. We will open-source all datasets, code, and model weights.