Accounts of human language processing have long appealed to implicit ``situation models'' that enrich comprehension with relevant but unstated world knowledge. Here, we apply causal intervention techniques to recent transformer models to analyze performance on the Winograd Schema Challenge (WSC), where a single context cue shifts interpretation of an ambiguous pronoun. We identify a relatively small circuit of attention heads that are responsible for propagating information from the context word that guides which of the candidate noun phrases the pronoun ultimately attends to. We then compare how this circuit behaves in a closely matched ``syntactic'' control where the situation model is not strictly necessary. These analyses suggest distinct pathways through which implicit situation models are constructed to guide pronoun resolution.

翻译：人类语言处理的解释长期以来依赖于隐含的“情境模型”，这些模型通过相关但未明确陈述的世界知识丰富理解过程。本文采用因果干预技术分析近期Transformer模型在Winograd模式挑战（WSC）上的表现，其中单个上下文线索改变了对歧义代词的解释。我们识别出一个相对较小的注意力头回路，该回路负责传播来自上下文单词的信息，从而引导代词最终关注哪个候选名词短语。随后，我们比较该回路在一个紧密匹配的“句法”控制组中的行为，该控制组中情境模型并非严格必要。这些分析揭示了构建隐含情境模型以指导代词消解的不同路径。