把大模型幻觉当作想象力，用于创意写作与虚拟叙事。
Purposefully Induced Psychosis (PIP): Embracing Hallucination as Imagination in Large Language Models
- 通过微调让大模型主动生成虚构、隐喻和超现实内容
- 在小说创作与沉浸式模拟中，幻觉反而激发创新思路
- 适合创意工作者和人机协作研究者探索新表达方式
大型语言模型（LLMs）中的幻觉通常被视为错误——即与事实不符的输出。然而，在创意或探索性场景中，这些‘错误’可能开启意想不到的创新路径。我们提出目的性诱导精神错乱（PIP），一种新方法，通过放大 LLM 的幻觉来支持推测性小说、互动叙事和混合现实模拟等想象任务。借鉴赫尔曼·梅尔维尔《白鲸》中皮普的‘疯狂’揭示深刻洞察，我们将幻觉重新定义为计算想象力的来源而非缺陷。该方法对模型进行微调，鼓励其生成具有推测性、隐喻性和超现实性的内容，当事实准确性并非首要目标时，这类幻觉具有实际价值。受剧场与舞台魔术中的共识幻觉启发，PIP 将这些创造性偏差置于用户自愿悬置信念的情境中，使‘错误’转化为新思维方式的催化剂。我们探讨了潜在应用、确保用户同意的设计原则、初步观察结果，以及对更广泛的人工智能伦理与人机协作的影响。
原文摘要 · Abstract (English)
Hallucinations in Large Language Models (LLMs) are widely regarded as errors - outputs that deviate from factual accuracy. However, in creative or exploratory contexts, these "mistakes" may represent unexpected avenues for innovation. We introduce Purposefully Induced Psychosis (PIP), a novel approach that amplifies LLM hallucinations for imaginative tasks such as speculative fiction, interactive storytelling, and mixed-reality simulations. Drawing on Herman Melville's Moby-Dick, where Pip's "madness" reveals profound insight, we reframe hallucinations as a source of computational imagination rather than a flaw. Our method fine-tunes LLMs to encourage speculative, metaphorical, and surreal outputs - hallucinations that are useful when factual accuracy is not the chief objective. Inspired by the consensual illusions of theater and stage magic, PIP situates these creative missteps in contexts where users willingly suspend disbelief, thereby transforming "errors" into catalysts for new ways of thinking. We discuss potential applications, design principles for ensuring user consent, preliminary observations, and implications for broader AI ethics and human-AI collaboration.
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。