Echo: A Large Language Model with Temporal Episodic Memory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, WenTao, Zhang, Ruohua, Zhou, Aimin, Gao, Feng, Liu, JiaLi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917934002077696
author Liu, WenTao
Zhang, Ruohua
Zhou, Aimin
Gao, Feng
Liu, JiaLi
author_facet Liu, WenTao
Zhang, Ruohua
Zhou, Aimin
Gao, Feng
Liu, JiaLi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_16090
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Echo: A Large Language Model with Temporal Episodic Memory
Liu, WenTao
Zhang, Ruohua
Zhou, Aimin
Gao, Feng
Liu, JiaLi
Computation and Language
Artificial Intelligence
Machine Learning
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.
title Echo: A Large Language Model with Temporal Episodic Memory
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2502.16090