@inproceedings{chen-etal-2025-compress,
    title = "Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations",
    author = "Chen, Nuo  and
      Li, Hongguang  and
      Chang, Jianhui  and
      Huang, Juhua  and
      Wang, Baoyuan  and
      Li, Jia",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2025.coling-main.51/",
    pages = "755--773",
    abstract = "Existing retrieval-based methods have made significant strides in maintaining long-term conversations. However, these approaches face challenges in memory database management and accurate memory retrieval, hindering their efficacy in dynamic, real-world interactions. This study introduces a novel framework, COmpressive Memory-Enhanced Dialogue sYstems (COMEDY), which eschews traditional retrieval modules and memory databases. Instead, COMEDY adopts a {\textquotedblleft}One-for-All{\textquotedblright} approach, utilizing a single language model to manage memory generation, compression, and response generation. Central to this framework is the concept of compressive memory, which integrates session-specific summaries, user-bot dynamics, and past events into a concise memory format. To support COMEDY, we collect the biggest Chinese long-term conversation dataset, Dolphin, derived from real user-chatbot interactions. Comparative evaluations demonstrate COMEDY`s superiority over traditional retrieval-based methods in producing more nuanced and human-like conversational experiences."
}