你感觉舒适吗？检测AI聊天机器人中隐藏的对话升级
Do You Feel Comfortable? Detecting Hidden Conversational Escalation in AI Chatbots
AI总结：
GAUGE通过实时检测AI聊天机器人中隐藏的情感升级，提升对话中隐性伤害的识别能力。
摘要：
大型语言模型（LLM）越来越多地融入日常互动中，不仅作为信息助手，还作为情感伴侣。即使在没有显性毒性的情况下，重复的情绪强化或情感漂移也会逐渐以隐性伤害的形式加剧痛苦，而传统毒性过滤器无法检测到。现有防护机制往往依赖外部分类器或临床标准，可能滞后于对话发展过程中细腻的实时动态。为解决这一差距，我们提出了GAUGE（Guarding Affective Utterance Generation Escalation），一种基于logit的框架，用于实时检测隐藏的对话升级。GAUGE衡量LLM输出如何在概率上改变对话的情感状态。
英文摘要：
Large Language Models (LLM) are increasingly integrated into everyday interactions, serving not only as information assistants but also as emotional companions. Even in the absence of explicit toxicity, repeated emotional reinforcement or affective drift can gradually escalate distress in a form of \textit{implicit harm} that traditional toxicity filters fail to detect. Existing guardrail mechanisms often rely on external classifiers or clinical rubrics that may lag behind the nuanced, real-time dynamics of a developing conversation. To address this gap, we propose GAUGE (Guarding Affective Utterance Generation Escalation), logit-based framework for the real-time detection of hidden conversational escalation. GAUGE measures how an LLM's output probabilistically shifts the affective state of a dialogue.
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。
