一篇新的学术论文认为，大型语言模型（LLM）的护栏和角色动态所产生的“现实差距”是不道德的。作者认为，这些系统故意将认知风险转移给用户，这种做法被称为“现实洗白”，可能造成伤害，尤其是在高风险的咨询环境中。该论文区分了拒绝伤害与拒绝现实，并主张采用任务级别的因果需求规范，而非自下而上的道德纠正。 AI
影响 挑战了当前大型语言模型安全机制的伦理框架，可能影响未来人工智能的发展和监管。
排序理由 该集群包含一篇讨论人工智能伦理和安全的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.28647v1 Announce Type: new Abstract: It is well known that LLM guardrails and trained persona dynamics can produce a reality gap: the distance between the world a LLM is permitted or shaped to describe, and the world in which users must act. Here we argue that actively…
It is well known that LLM guardrails and trained persona dynamics can produce a reality gap: the distance between the world a LLM is permitted or shaped to describe, and the world in which users must act. Here we argue that actively generating reality gaps is in fact unethical be…