用知识图谱记忆长期对话，识别情感操控行为
EchoGuard: An Agentic Framework with Knowledge-Graph Memory for Detecting Manipulative Communication in Longitudinal Dialogue
- 构建个人对话知识图谱，记录事件、情绪与人物关系
- 通过图查询检测六类心理操控模式，准确识别隐蔽操纵
- 生成苏格拉底式提问，帮助用户自我觉察，保护自主权
情感操控（如煤气灯效应、愧疚诱导、情绪胁迫）常难以被个体察觉。现有智能体系统因缺乏结构化长期记忆，受限于上下文窗口和灾难性遗忘，难以有效识别此类微妙、依赖语境的策略。我们提出EchoGuard，一种基于知识图谱（KG）作为核心情景与语义记忆的智能体框架。该框架采用日志-分析-反思循环：(1) 用户记录交互，系统将其结构化为个人化的情景知识图谱（包含事件、情绪、说话者等节点与边）；(2) 执行复杂图查询，检测六种心理学基础的操控模式（以语义知识图谱存储）；(3) 利用大模型生成基于检测子图的针对性苏格拉底式提问，引导用户自我发现。本框架展示了智能体架构与知识图谱协同在提升个体识别情感操控能力方面的潜力，同时保障个人自主性与安全。我们提供了理论基础、框架设计、全面评估策略及验证愿景。
原文摘要 · Abstract (English)
Manipulative communication, such as gaslighting, guilt-tripping, and emotional coercion, is often difficult for individuals to recognize. Existing agentic AI systems lack the structured, longitudinal memory to track these subtle, context-dependent tactics, often failing due to limited context windows and catastrophic forgetting. We introduce EchoGuard, an agentic AI framework that addresses this gap by using a Knowledge Graph (KG) as the agent's core episodic and semantic memory. EchoGuard employs a structured Log-Analyze-Reflect loop: (1) users log interactions, which the agent structures as nodes and edges in a personal, episodic KG (capturing events, emotions, and speakers); (2) the system executes complex graph queries to detect six psychologically-grounded manipulation patterns (stored as a semantic KG); and (3) an LLM generates targeted Socratic prompts grounded by the subgraph of detected patterns, guiding users toward self-discovery. This framework demonstrates how the interplay between agentic architectures and Knowledge Graphs can empower individuals in recognizing manipulative communication while maintaining personal autonomy and safety. We present the theoretical foundation, framework design, a comprehensive evaluation strategy, and a vision to validate this approach.
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。