Bridging Intuitive Associations and Deliberate Recall: Empowering LLM Personal Assistant with Graph-Structured Long-term Memory

ACL ARR 2025 February Submission8014 Authors

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 **Associa**, a graph-structured memory framework that mimics human cognitive processes. Associa comprises an event-centric memory graph and two collaborative components: **Intuitive Association**, which extracts evidence-rich subgraphs through Prize-Collecting Steiner Tree optimization, and **Deliberating Recall**, which iteratively refines queries for comprehensive evidence collection. Experiments show that Associa significantly outperforms existing methods in retrieval metrics and user preference across dialogue benchmarks, advancing the development of more human-like AI memory systems.

Paper Type: Long

Research Area: Information Retrieval and Text Mining

Research Area Keywords: dense retrieval

Languages Studied: English

Submission Number: 8014