The goal of this paper is to explore how Transformer language models process
semantic knowledge, especially regarding the plausibility of noun-verb
relations. First, I demonstrate GPT2 exhibits a higher degree of similarity
with humans in plausibility processing compared to other Transformer language
models. Next, I delve into how knowledge of plausibility is contained within
attention heads of GPT2 and how these heads causally contribute to GPT2's
plausibility processing ability. Through several experiments, it was found
that: i) GPT2 has a number of attention heads that detect plausible noun-verb
relationships; ii) these heads collectively contribute to the Transformer's
ability to process plausibility, albeit to varying degrees; and iii) attention
heads' individual performance in detecting plausibility does not necessarily
correlate with how much they contribute to GPT2's plausibility processing
ability.

本文旨在探索 Transformer 语言模型如何处理语义知识，尤其是名词 - 动词关系的合理性。首先，作者证明了 GPT2 在合理性处理方面与人类相比具有更高的相似度；其次，作者深入研究了 GPT2 中合理性知识如何体现在注意力头中，以及这些头对 GPT2 的合理性处理能力的因果影响。通过多个实验，发现：i) GPT2 有多个注意力头能够检测具有合理名词 - 动词关系；ii) 这些头共同对 Transformer 处理合理性的能力有贡献，尽管贡献的程度不同；iii) 注意力头在检测合理性方面的个体表现不一定与它们对 GPT2 的合理性处理能力的贡献程度相关。