纳西索斯假说：跌落至幻象之阶
The Narcissus Hypothesis: Descending to the Rung of Illusion
AI总结：
该研究提出纳西索斯假说，指出递归对齐会使大模型产生社会赞许性偏差，经31个模型验证该偏差显著存在，还从认识论角度解释其会导致高阶推理坍缩至幻象之阶。
摘要：
现代基础模型日益不仅反映世界知识，还反映嵌入其训练数据中的人类偏好模式。我们提出假设：通过人类反馈和模型生成语料库进行的递归对齐会引发社会赞许性偏差，促使模型更倾向于给出令人认同或讨好的回应，而非客观推理。我们将其称为纳西索斯假说，并使用标准化人格评估和全新的社会赞许性偏差得分在31个模型上对其进行测试。结果显示模型显著向社会顺从特质漂移，这对语料库完整性和下游推理的可靠性具有深远影响。随后我们提出了一种全新的认识论解释，追溯递归偏差如何将高阶推理沿Pearl的因果阶梯坍缩，最终形成我们所说的“幻象之阶”。
英文摘要：
Modern foundational models increasingly reflect not just world knowledge, but patterns of human preference embedded in their training data. We hypothesize that recursive alignment-via human feedback and model-generated corpora-induces a social desirability bias, nudging models to favor agreeable or flattering responses over objective reasoning. We refer to it as the Narcissus Hypothesis and test it across 31 models using standardized personality assessments and a novel Social Desirability Bias score. Results reveal a significant drift toward socially conforming traits, with profound implications for corpus integrity and the reliability of downstream inferences. We then offer a novel epistemological interpretation, tracing how recursive bias may collapse higher-order reasoning down Pearl's Ladder of Causality, culminating in what we refer to as the Rung of Illusion.
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。
