LCAM：诊断对话式AI中交互对齐失败的框架
LCAM: A Framework for Diagnosing Interactional Alignment Failures in Con-versational AI
AI总结：
提出分层认知对齐模型（LCAM），通过五层对齐和两种失调极性诊断对话式AI的交互失败，应用于LLM咨询案例揭示潜在危害。
摘要：
对话式AI越来越多地用于用户可能脆弱、不确定或依赖系统表面能力的场景中，提供建议、解释、安慰和决策支持。现有的对齐工作通常关注模型目标、偏好优化或输出正确性。然而，许多危害源于交互：系统如何构建权威、表达不确定性、模拟共情、支持推理以及使边界清晰。本文介绍了分层认知对齐模型（LCAM），这是一个用于诊断对话式AI中交互对齐失败的概念性和规范性框架。LCAM将对齐定义为系统行为、用户目标、任务需求和规范性上下文之间的校准匹配。它区分了五个匹配层：感知层、语义层、情感层、认知层和伦理层，以及两种失调极性：欠拟合和过度延伸。我们将LCAM应用于一个已发表的LLM咨询示例，展示了一个看似支持性的回应如何强化有害信念、模拟不适当的关怀并模糊角色边界。通过将对话失败转化为关于过度依赖、虚假亲密、自主性侵蚀、边界混淆和不适当信任的审计和治理问题，LCAM提供了一个超越准确性、有用性或信任度的评估对话式AI的理论和规范性视角。
英文摘要：
Conversational AI is increasingly used for advice, interpretation, reassurance, and decision support in contexts where users may be vulnerable, uncertain, or dependent on the system's apparent competence. Existing alignment work often focuses on model objectives, preference optimization, or output correctness. Yet, many harms arise through interaction: how systems frame authority, express uncertainty, simulate empathy, support reasoning, and make boundaries legible. This paper introduces the Layered Cognitive Alignment Model (LCAM), a conceptual and normative framework for diagnosing interac-tional alignment failures in conversational AI. LCAM defines alignment as a calibrated fit among system behavior, user goals, task demands, and normative context. It distinguishes five layers of fit: perceptual, semantic, affective, cognitive, and ethical, and two diagnostic polarities of misalignment: underfit and overreach. We apply LCAM to a published LLM counseling example, showing how an apparently supportive response can reinforce harmful beliefs, simulate inappropriate care, and obscure role boundaries. By translating conversational failures into audit and governance questions concerning over-reliance, false intimacy, autonomy erosion, boundary confusion, and inappropriate trust, LCAM offers a theoretical and normative lens for evaluating conversational AI beyond accuracy, helpfulness, or trust.
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。
