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

Ryuichi Sumida, Koji Inoue, Tatsuya Kawahara


Abstract
This study addresses the issue of what a Retrieval-Augmented Generation (RAG) chatbot should remember and what it should forget, based on findings from psychology. RAG retrieves relevant memories from past interactions to generate responses, and its effectiveness has been demonstrated. As conversations continue, however, the amount of stored memory keeps growing, which not only requires large storage capacity but also risks retaining unnecessary information, potentially reducing retrieval efficiency.To tackle this problem, we propose LUFY (Long-term Understanding and identiFYing key exchanges), a RAG chatbot that evaluates six distinct memory-related metrics derived from psychological models and real-world data. Instead of simply summing these metrics, it uses learned weights to account for the importance of each one. By using these weighted scores, the system can prioritize and retain relevant memories while gradually forgetting less important ones during both retrieval and memory management.To evaluate the effectiveness of LUFY in long-term conversations, we conducted experiments with human participants, who engaged in text-based conversations with three types of chatbots, each using different forgetting mechanisms, for at least two hours. The length of these conversations was more than 4.5 times longer than the longest conversations reported in previous studies. The results showed that prioritizing emotionally engaging memories while forgetting most of the conversation significantly enhanced user satisfaction.
Anthology ID:
2025.dnd-16.12
Volume:
Dialogue Discourse Volume 16
Month:
December
Year:
2025
Address:
Chicago, Illinois, USA
Editors:
Amir Zeldes, Manfred Stede, Patrick G.T. Healey, and Hendrik Buschmeier
Venue:
DND
SIG:
SIGDIAL
Publisher:
University of Illinois Chicago
Note:
Pages:
74–110
Language:
URL:
https://aclanthology.org/2025.dnd-16.12/
DOI:
10.5210/dad.2025.203
Bibkey:
Cite (ACL):
Ryuichi Sumida, Koji Inoue, and Tatsuya Kawahara. 2025. Enhancing Long-term RAG Chatbots with Psychological Models of Memory Importance and Forgetting. Dialogue & Discourse, 16:74–110.
Cite (Informal):
Enhancing Long-term RAG Chatbots with Psychological Models of Memory Importance and Forgetting (Sumida et al., DND 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.dnd-16.12.pdf