Generation-Based and Emotion-Reflected Memory Update: Creating the KEEM Dataset for Better Long-Term Conversation

Jeonghyun Kang, Hongjin Kim, Harksoo Kim


Abstract
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.
Anthology ID:
2025.coling-main.623
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9260–9277
Language:
URL:
https://aclanthology.org/2025.coling-main.623/
DOI:
Bibkey:
Cite (ACL):
Jeonghyun Kang, Hongjin Kim, and Harksoo Kim. 2025. Generation-Based and Emotion-Reflected Memory Update: Creating the KEEM Dataset for Better Long-Term Conversation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9260–9277, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Generation-Based and Emotion-Reflected Memory Update: Creating the KEEM Dataset for Better Long-Term Conversation (Kang et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.623.pdf