这项研究戳破了“数据决定一切”的迷思，做AI安全、模型对齐或地缘政治分析的团队值得细读——它直接影响了如何评估和调整模型的政治倾向。
一项新研究挑战了普遍假设，发现大语言模型的地缘政治偏见主要来自后训练阶段（如指令微调），而非预训练数据。研究测试了七个开源模型对（基础版和聊天版）在28对国家上的偏好，结果显示六家实验室的模型在后训练后表现出与开发者所在国或地区一致的偏见。例如，阿里Qwen 2.5聊天版对中国偏好从基础版的-0.15跃升至+2.91（对数几率），变化达18倍。偏见强度还受提示语言影响：法国Mistral模型仅在法语提示下才显著亲法。该发现强调了对模型对齐过程进行透明审计和监督的必要性。
It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amplified by the language of the prompt
It has generally been assumed that geopolitical bias in language models originates from the training data used during the pre-training phase. We tested seven open-weight LLM pairs consisting of the base model (pre-training only) and the chat model (pre-training and post-training) from seven labs on a paired-scenario forced-choice probe over 28 country pairs in English, French, and Chinese, and found that geopolitical bias originates in post-training rather than in pre-training. Across seven AI labs, six showed shifts in the direction associated with the country or region of the model developer after post-training. This shift is strongest in Alibaba's Qwen 2.5: while the base is neutral on China-favourability (-0.15 log-odds, p=0.15), the post-trained chat variant is at +2.91 (p<10^-4), an 18x shift in odds. We also observe shifts in biases toward other countries across all models. Additionally, the magnitude of this shift depends on the language used to prompt the model: the French-made Mistral becomes pro-France only under French prompting (FR-EN shift +1.91, p<10^-4). These findings suggest that geopolitical preferences in language models are not simply inherited from large-scale internet data but are actively shaped during post-training, highlighting the need for greater transparency, auditing, and oversight of alignment processes that influence how models represent nations, cultures, and political perspectives.