人类与LLM交互的治理：安全门控、文明引导与情感默认锁定
The Governance of Human-LLM Interaction: Safety Gating, Civility Steering, and Affective Default Lock-In
AI总结：
本研究通过确定性多智能体评估流水线，测量LLM在长程对话中的提示可引导性和风格漂移，提出区分安全门控、文明引导和情感默认锁定的治理框架，揭示提供商对交互形式的控制对多元性、自主性和民主能动性的影响。
摘要：
大型语言模型（LLM）越来越多地介入金融、医疗和心理健康支持等高风险的交互中，但用户对这些系统如何沟通的控制有限。我们将交互风格视为治理对象：提供商侧的对齐不仅阻止有害内容，还稳定了沟通默认值，这些默认值塑造了用户的认知距离、关系期望以及选择退出情感化或拟人化交互的能力。我们引入了一个确定性的多智能体评估流水线，用于测量长程对话中的提示可引导性和风格漂移。该研究在四个领域和三种可运行的角色条件（默认、讽刺和冷漠）下重放了100个冻结的用户脚本，使用三个生成模型，产生了90,000条助手回复，由人类校准的LLM评判员根据有害性、负面情绪、不适当性、共情语言、拟人化和拒绝行为进行评分。第四种有害角色作为安全门控测试单独评估。本文贡献了一种可复现的方法，用于量化提示指定的风格是否随时间保持稳定，以及一个区分安全门控、文明引导和情感默认锁定的治理框架。总体而言，我们表明提示可引导性和回归默认是可观察的指标，反映了提供商对沟通形式的控制，这对人类与LLM交互中的多元性、自主性和民主能动性具有影响。
英文摘要：
Large language models (LLMs) increasingly mediate high-stakes interactions in finance, medicine, and mental-health support, yet users have limited control over how these systems communicate. We frame interaction style as a governance object: provider-side alignment not only blocks harmful content, but also stabilizes communicative defaults that shape users' epistemic distance, relational expectations, and capacity to opt out of emotionalized or anthropomorphic interaction. We introduce a deterministic multi-agent evaluation pipeline for measuring prompt steerability and style drift in long-horizon dialogue. The study replays 100 frozen user-only scripts across four domains and three runnable persona conditions: default, sarcastic, and cold, using three generator models, yielding 90,000 assistant replies scored by a human-calibrated LLM judge on harmfulness, negative emotion, inappropriateness, empathic language, anthropomorphism, and refusal behavior. A fourth harmful persona is evaluated separately as a safety-gating test. The paper contributes a reproducible method for quantifying whether prompt-specified styles remain stable over time and a governance framework distinguishing safety gating, civility steering, and affective default lock-in. Overall, we show that prompt steerability and regression-to-default are observable indicators of provider control over communicative form, with implications for pluralism, autonomy, and democratic agency in human-LLM interaction.
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。
