SLIP与伦理：面向AI情感伴侣的渐进干预
SLIP & ETHICS: Graduated Intervention for AI Emotional Companions
AI总结：
本文提出SLIP与ETHICS框架，通过渐进干预方法解决AI情感伴侣的安全与亲和力矛盾，实验显示在高能量状态下干预不足，但提升模型能力可改善检测效果。
摘要：
AI情感伴侣面临安全与亲和力的矛盾：严格的安全措施可能损害支持性联盟，而宽松的系统则可能危害用户。本文提出SLIP（分阶段干预协议），一种四阶段渐进方法，通过结构化定性指标（情绪强度(a)和叙述动态性(m)）推导干预措施（无、轻度、重度）。ETHICS（人类-人工智能交互上下文信号的新兴分类法）是一种“信号而非标签”的分类法。结合小规模生产部署（N=68，10名用户，10周）和合成角色电池测试（N=91，5种行为风险配置文件），结果显示流角色的误报率为0%，并在危机导向角色中显示出预期的升级模式。然而，初步结果表明，连续8天的高能量提升导致零干预（0/8），暴露了“不病理化”原则与安全之间的边界。后续的三模型压力测试显示，增加模型能力可将检测率从0/8提升至6/8，同时在最大模型中保持0/10的流误报率。这些发现将渐进干预作为导航而非解决情感计算中安全与亲和力张力的设计方向。
英文摘要：
AI emotional companions face a safety-rapport paradox: restrictive safeguards can damage supportive alliance, while permissive systems risk user harm. We present SLIP (Staged Layers of Intervention Protocol), a four-stage graduated methodology deriving interventions (none, soft, hard) from structured qualitative indicators -- affect intensity (a) and narrative dynamism (m) -- alongside ETHICS (Emergent Taxonomy for Human-AI Interaction Context Signals), a "signals not labels" taxonomy. An evaluation combining a small-scale production deployment (N=68 entries, 10 users, 10 weeks) with a synthetic persona battery (N=91, 5 behavioral-risk profiles) achieved 0% false positives for the flow persona and showed expected escalation patterns in crisis-oriented personas. However, initial results showed that 8 consecutive days of high-energy elevation produced zero interventions (0/8), exposing a boundary where the "do not pathologize" principle conflicts with safety. A subsequent three-model stress test demonstrated that increased model capability improves detection from 0/8 to 6/8 while preserving 0/10 flow false positives in the largest model. Read as preliminary, these findings position graduated intervention as a design direction for navigating -- not resolving -- the safety-rapport tension in affective computing.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
