为低密度长对话设计细粒度情感支持记忆框架
FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue
- 按情境片段分割对话，构建事实-时间-情绪联合记忆单元
- 在ES-MemEval上达0.3871 F1和0.6668 BERTScore
- 适合需要长期个性化理解的对话系统研发者
长时情感支持对话系统需具备跨会话的个性化记忆能力。然而情感支持对话常具低密度特征：对话轮次不完整、信息零散且用户状态持续演变。现有记忆方法多依赖固定单元（如轮次笔记或会话摘要），易丢失细节或引入冗余噪声。本文提出FTA-Mem，一种面向低密度长对话的结构化记忆框架。通过边界保持的窗口分割（BWS）生成连贯情境片段，并构建融合事实内容、时间定位与情感上下文的FTA记忆单元。检索到的单元被合成结构化上下文用于生成回复。在ES-MemEval与LoCoMo数据集上的实验表明，FTA-Mem在不同信息密度特性下均提升长期记忆问答性能。在ES-MemEval上取得0.3871 F1与0.6668 BERTScore。进一步分析显示，情境级的FTA构建在证据保留与构建成本间实现更优权衡，优于粗粒度会话级或过细粒度的成对轮次构造，为长对话记忆提供有效粒度选择。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。