18个开源大模型能认出宙斯，却难辨非主流神话人物。
Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMs
- 用多种分析工具定位文化知识在模型中的存储位置
- 文化特征被保留但读取时被主导传统覆盖
- 模型对不同语言的提问反应不同，读取受提示语种限制
开源大模型能稳定识别宙斯、朱庇特和托尔等名字，但在芬兰、斯拉夫、埃及或中国神话中对应人物的识别一致性显著下降。我们通过跨文化汤普森母题实体数据集，对18个来自8种架构家族的开源LLM进行线性探测、逻辑镜头、激活修补和输出提取分析。残差流可清晰区分文化，远超名称字符串基线；但解码器将文化特异性标记坍缩为占主导地位的传统标记。问题出在读取阶段而非表征阶段。以目标文化的母语或英语提问，失败模式在语言内部聚集但跨语言解耦：解码器受提示语言制约。我们发布每实体的（探测器、输出）分解框架、引用锚定的跨文化基准数据、语言条件读取的组内与跨组相关性测试方法，以及所有18个模型的每实体预测结果。
原文摘要 · Abstract (English)
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.
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。