论文发现 LLM 潜在空间自发形成荣格原型结构
The Mathematical Collective Unconscious: Jungian Archetypes within the Latent Space
有人拿 text-embedding-3-small 跑了 13 组实验，发现梦境文本真的聚在'阴影''捣蛋鬼'那几个区域，民间故事反而摊得很匀，挺有意思的解读角度。
arXiv 论文 2610.15678v1 探索 LLM 潜在空间是否自发形成类似荣格集体无意识原型的分区。作者用 OpenAI 的 text-embedding-3-small 模型，在 13 组实验中结合余弦相似度与角距离指标，测试对象涵盖合成叙事、Shmoop 文学语料、DreamBank 梦境报告和 Andrew Lang 童话集。结果显示原型角色在潜在空间中占据可测量的独立区域，且由叙事结构而非词汇重叠维持。梦境报告集中在 Trickster 与 Shadow 区域，传统民间故事则在所有原型上均匀分布。
The Mathematical Collective Unconscious: Jungian Archetypes within the Latent Space
Carl Jung theorised that the human psyche contains an inherited framework, the collective unconscious, populated by universal archetypes. As large language models (LLMs) are trained on vast corpora of textual data, this paper investigates whether they spontaneously construct distinct archetype-like regions within their high-dimensional latent spaces. The paper proposes that these regions function as spatial constraints that naturally organise semantically related narratives. To evaluate this, we applied cosine similarity and angular distance metrics across thirteen experiments utilising OpenAIs text-embedding-3-small model. The paper contains two experimental sections the first section explores these ideas using synthetically constructed narratives, the results of which act as a baselines for experiments conducted in the second section where the synthetic data is replaced by human-authored literature (Shmoop corpus), unedited dream reports (DreamBank corpus), and culturally distilled folklore (Andrew Langs Fairy Books). The results show that archetypal roles occupy distinct, measurable regions in the latent space. Crucially, these regions remain compact and consistent because of narrative structure rather than simple word overlap. Additionally, text category dictates spatial distribution: dream reports concentrate within Trickster and Shadow regions, while traditional folklore distributes evenly across all tested archetypes. We conclude that transformer latent spaces encode stable regions which appear to correspond to recognised Jungian archetypes.
