@inproceedings{zhang-etal-2025-bridging,
    title = "Bridging Intuitive Associations and Deliberate Recall: Empowering {LLM} Personal Assistant with Graph-Structured Long-term Memory",
    author = "Zhang, Yujie  and
      Yuan, Weikang  and
      Jiang, Zhuoren",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/declare-journal/2025.findings-acl.901/",
    doi = "10.18653/v1/2025.findings-acl.901",
    pages = "17533--17547",
    ISBN = "979-8-89176-256-5",
    abstract = "Large language models (LLMs)-based personal assistants may struggle to effectively utilize long-term conversational histories.Despite advances in long-term memory systems and dense retrieval methods, these assistants still fail to capture entity relationships and handle multiple intents effectively. To tackle above limitations, we propose \textbf{Associa}, a graph-structured memory framework that mimics human cognitive processes. Associa comprises an event-centric memory graph and two collaborative components: \textbf{Intuitive Association}, which extracts evidence-rich subgraphs through Prize-Collecting Steiner Tree optimization, and \textbf{Deliberating Recall}, which iteratively refines queries for comprehensive evidence collection. Experiments show that Associa significantly outperforms existing methods in retrieval and QA (question and answering) tasks across long-term dialogue benchmarks, advancing the development of more human-like AI memory systems."
}