PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering

TL;DR

This paper introduces PerLTQA, a comprehensive dataset and framework for integrating personalized long-term memories into question answering systems, enhancing their ability to leverage historical and social information.

Contribution

The paper presents a novel dataset combining semantic and episodic memories and proposes a framework for memory classification, retrieval, and synthesis in QA tasks, with extensive evaluation.

Findings

BERT-based models outperform LLMs in memory classification

Effective memory integration improves QA performance

PerLTQA enables exploration of personalized memory in LLMs

Abstract

Long-term memory plays a critical role in personal interaction, considering long-term memory can better leverage world knowledge, historical information, and preferences in dialogues. Our research introduces PerLTQA, an innovative QA dataset that combines semantic and episodic memories, including world knowledge, profiles, social relationships, events, and dialogues. This dataset is collected to investigate the use of personalized memories, focusing on social interactions and events in the QA task. PerLTQA features two types of memory and a comprehensive benchmark of 8,593 questions for 30 characters, facilitating the exploration and application of personalized memories in Large Language Models (LLMs). Based on PerLTQA, we propose a novel framework for memory integration and generation, consisting of three main components: Memory Classification, Memory Retrieval, and Memory Synthesis. We evaluate this framework using five LLMs and three retrievers. Experimental results demonstrate that BERT-based classification models significantly outperform LLMs such as ChatGLM3 and ChatGPT in the memory classification task. Furthermore, our study highlights the importance of effective memory integration in the QA task.