Generation-Based and Emotion-Reflected Memory Update: Creating the KEEM Dataset for Better Long-Term Conversation
This addresses the issue of information conflicts and inaccurate user state tracking in conversational AI, though it appears incremental as it builds on existing memory update methods.
The paper tackled the problem of memory updates in long-term conversational systems by introducing the KEEM dataset, which dynamically generates integrative memories to preserve essential facts and emotional context, resulting in enhanced empathy and meaningful responses in open-domain conversations.
In this work, we introduce the Keep Emotional and Essential Memory (KEEM) dataset, a novel generation-based dataset designed to enhance memory updates in long-term conversational systems. Unlike existing approaches that rely on simple accumulation or operation-based methods, which often result in information conflicts and difficulties in accurately tracking a user's current state, KEEM dynamically generates integrative memories. This process not only preserves essential factual information but also incorporates emotional context and causal relationships, enabling a more nuanced understanding of user interactions. By seamlessly updating a system's memory with both emotional and essential data, our approach promotes deeper empathy and enhances the system's ability to respond meaningfully in open-domain conversations.