We ask whether multilingual language models trained on unbalanced, English-dominated corpora use English as an internal pivot language -- a question of key importance for understanding how language models function and the origins of linguistic bias. Focusing on the Llama-2 family of transformer models, our study uses carefully constructed non-English prompts with a unique correct single-token continuation. From layer to layer, transformers gradually map an input embedding of the final prompt token to an output embedding from which next-token probabilities are computed. Tracking intermediate embeddings through their high-dimensional space reveals three distinct phases, whereby intermediate embeddings (1) start far away from output token embeddings; (2) already allow for decoding a semantically correct next token in the middle layers, but give higher probability to its version in English than in the input language; (3) finally move into an input-language-specific region of the embedding space. We cast these results into a conceptual model where the three phases operate in "input space", "concept space", and "output space", respectively. Crucially, our evidence suggests that the abstract "concept space" lies closer to English than to other languages, which may have important consequences regarding the biases held by multilingual language models.

翻译：我们探究了在不平衡、以英语为主的数据上训练的多语言语言模型是否将英语作为内部枢轴语言——这一问题的回答对理解语言模型的运行机制及语言偏见的根源至关重要。本研究聚焦于Llama-2系列Transformer模型，通过精心构造具有唯一正确单词元延续的非英语提示，逐层追踪Transformer将输入提示中最终词元的嵌入映射至输出嵌入（用于计算下一词元概率）的完整过程。高维空间中中间嵌入的轨迹揭示了三个截然不同的阶段：第一阶段，中间嵌入初始位置远离输出词元嵌入；第二阶段，中间层已可解码出语义正确的下一个词元，但该词元的英语版本概率高于输入语言版本；第三阶段，中间嵌入最终移动至输入语言专属的嵌入空间区域。我们将这些发现凝练为概念模型，分别对应“输入空间”、“概念空间”与“输出空间”三阶段运作机制。关键证据表明，抽象的“概念空间”更接近英语而非其他语言，这一发现对理解多语言语言模型所持偏见具有重要启示意义。