Enhancing Long-term RAG Chatbots with Psychological Models of Memory Importance and Forgetting

TL;DR

This paper introduces LUFY, a memory management method for long-term RAG chatbots that prioritizes emotionally arousing memories and forgets most conversation content, significantly improving user experience.

Contribution

The paper presents a novel memory prioritization approach based on psychological models, extending long-term chatbot capabilities beyond existing benchmarks.

Findings

Prioritizing emotionally arousing memories improves user engagement.

Forgetting over 90% of conversation content enhances retrieval accuracy.

LUFY outperforms existing methods in long-term chatbot experiments.

Abstract

While Retrieval-Augmented Generation (RAG) has shown promise in enhancing long-term conversations, the increasing memory load as conversations progress degrades retrieval accuracy. Drawing on psychological insights, we propose LUFY, a simple yet effective method that focuses on emotionally arousing memories and retains less than 10% of the conversation. In the user experiment, participants interacted with three types of RAG chatbots, each for 2 hours over 4 sessions, marking the most extensive assessment of a chatbot's long-term capabilities to date -- more than four times longer than any existing benchmark. The results demonstrate that prioritizing arousing memories while forgetting the majority of the conversation significantly enhances user experience. This study pushes the frontier of long-term conversations and highlights the importance of forgetting unimportant parts of conversations. Code and Dataset: https://github.com/ryuichi-sumida/LUFY, Hugginface Dataset:https://huggingface.co/datasets/RuiSumida/LUFY