这篇论文用18个模型告诉你：LLM其实知道芬兰神话，但输出时故意不说。想看AI文化偏见的根源，读这篇。
一项研究对18个开源大模型进行跨文化神话知识探测，覆盖8个架构家族。模型能准确识别宙斯、朱庇特、托尔，但在芬兰、斯拉夫、埃及或中国神话中表现明显下降。研究者使用线性探针、logit lens、激活修补等方法，发现残差流能清晰区分文化，但解码器将特定文化token坍缩为主导传统。失败发生在读出阶段而非表征阶段，且解码行为受提示语言门控。论文发布了逐实体分解框架、跨文化基准及18个模型的预测结果。
Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMs
Open-source LLMs reliably name Zeus, Jupiter, and Thor, but recover their counterparts in less-represented traditions like Finnish, Slavic, Egyptian, or Chinese mythology far less consistently. We ask where inside the model this cultural default is produced. On a parallel cross-cultural substrate of Thompson-motif entities, we instrument 18 open-source LLMs from 8 architecture families with linear probing, logit lens, activation patching, and output extraction. The residual stream cleanly distinguishes cultures, well above a name-string baseline, yet the decoder collapses culturally-specific tokens onto dominant-tradition ones. The failure is at readout, not at representation. Asking the same question in the target culture's native language versus English produces failures that cluster within language but decouple across language: the decoder is gated on prompt language. We release a per-entity (probe, output) decomposition framework, a citation-anchored cross-cultural ground truth, a within- versus cross-mode correlation test for language-conditioned readout, and per-entity predictions for all 18 models.