FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue
2026-08-17 • Computation and Language
Computation and Language
AI summaryⓘ
The authors address the challenge of remembering important details in long conversations that provide emotional support, where information is often scattered and incomplete. They introduce FTA-Mem, a memory system that breaks conversations into meaningful chunks and stores facts, time, and emotions together for better understanding. This method helps the system remember relevant information more effectively than previous approaches. Their tests showed improved performance in answering questions about long-term conversations. The authors also found their method strikes a good balance between keeping enough detail and avoiding too much complexity.
emotional-support dialoguelong-term memoryBoundary-preserving Window SegmentationFact-Time-Affect Memory Unitsdialogue systemscontext representationmemory retrievalquestion answeringinformation granularityBERTScore
Authors
Chang Liu, Shuyi Zhang, Changsheng Ma, Yongfeng Tao, Minqiang Yang, Bin Hu
Abstract
Long-term emotional-support agents require memory mechanisms for personalized understanding across sessions. However, emotional-support dialogue is often low-density: turns are incomplete, evidence is scattered, and user states evolve over time. Existing memory methods usually rely on fixed units, such as turn-level notes or session summaries, which may lose details or introduce redundant noise. We propose FTA-Mem, a structured memory framework for low-density long-term dialogue. FTA-Mem uses Boundary-preserving Window Segmentation (BWS) to form coherent situation fragments, and constructs Fact-Time-Affect Memory Units (FTA Units) that jointly encode factual content, temporal grounding, and affective context. Retrieved units are then synthesized into structured context for answer generation. Experiments on ES-MemEval and LoCoMo show that FTA-Mem improves overall long-term memory question answering across benchmarks with different information-density characteristics. On ES-MemEval, FTA-Mem achieves 0.3871 F1 and 0.6668 BERTScore. Further analysis shows that situation-level FTA construction better balances evidence preservation and construction cost than coarse session-level or overly fine-grained turn-pair construction, providing an effective granularity trade-off for long-term dialogue memory.