Enhancing Long-term RAG Chatbots with Psychological Models of Memory Importance and Forgetting
This work addresses the challenge of maintaining performance in long-term conversations for RAG chatbots, representing an incremental improvement by applying psychological models to a known bottleneck.
The paper tackled the problem of degrading retrieval accuracy in long-term RAG chatbots due to increasing memory load, by proposing LUFY, a method that focuses on emotionally arousing memories and retains less than 10% of conversation, resulting in significantly enhanced user experience in extensive user experiments.
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