研究人机关系如何随时间演变，发现记忆感知与互动转折点是关键。
Memory-Driven Self-Disclosure and Relational Turning Points: A Longitudinal Multimodal Study of Human-AI Interaction
- 通过24人×10次会话的多模态追踪，分析关系演化机制。
- 感知记忆影响后续自我披露，进而提升长期愉悦感。
- 关系存在突变节点，行为信号可提前预警或捕捉高潮期。
随着对话式AI系统被持续使用，核心问题在于一系列交互如何形成关系。本研究开展了一项纵向多模态研究，考察了24名参与者在10次会话中对记忆增强型对话代理的体验。每次会话后，参与者评估五个关系维度：熟悉度、自我披露、感知记忆、对话质量与愉悦感。研究发现两种互补动态：第一，对话质量显著影响即时愉悦感但不跨会话延续；而感知记忆具有关系依赖性——由先前关系状态预测，而非仅反映系统能力，并通过后续自我披露间接影响后期愉悦感。第二，关系呈现离散转折点（崩溃与飙升），其部分可从多模态行为中识别，为干预提供窗口：飙升更易实时检测，愉悦飙升比崩溃恢复更持久；某些崩溃可通过个体行为漂移提前预测，而非事后察觉。整体表明，长期人机关系既通过缓慢积累，也经由突发转折构建。
原文摘要 · Abstract (English)
As conversational AI systems are designed for repeated use, a central question is how a series of interactions becomes a relationship. We present a longitudinal multimodal study of a memory-augmented conversational agent (24 participants x 10 sessions), in which participants rated five relational constructs -- familiarity, self-disclosure, perceived memory, conversational quality, and enjoyment -- after each session. Two complementary dynamics emerge. First, conversational quality strongly shapes how enjoyable a session feels in the moment but does not carry forward across sessions, whereas perceived memory is relationally conditioned -- predicted by prior relational state rather than reflecting system capability alone -- and it shapes later enjoyment indirectly, via subsequent self-disclosure. Second, relationships are punctuated by discrete turning points -- crashes and surges -- that are partially traceable in multimodal behavior and open different intervention windows: surges are more behaviorally detectable in the moment, enjoyment surges persist more reliably than enjoyment crashes recover, and some crashes are better forecast from person-specific behavioral drift than detected after they have already occurred. Together, the findings suggest that longitudinal human-AI relationships are built through both slow accumulation and abrupt turning points.
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。