语言模型是否表现出类人的结构启动效应？
Do Language Models Exhibit Human-like Structural Priming Effects?
AI总结：
该研究采用结构启动范式探究语言模型是否存在类人结构启动效应，发现逆频率效应和词汇依存性可解释该效应，为理解上下文对语言模型结构预测的影响提供了关键依据。
摘要：
我们探究了句子层面和词元层面的哪些语言学因素在影响语言模型预测中发挥重要作用，并研究这些因素是否反映了在人类及人类语料库中发现的结果（Gries and Kootstra, 2017）。我们采用了结构启动范式，即近期接触过某一结构会促进对相同结构的加工。我们不仅研究启动效应是否存在，还探究其发生的位置以及预测启动效应的因素。研究表明，这些效应可以通过人类启动研究中已知的逆频率效应（即启动项中更罕见的元素会增强启动效应）以及启动项与目标项之间的词汇依存性来解释。我们的研究结果为理解上下文属性如何影响语言模型的结构预测这一谜题提供了重要线索。
英文摘要：
We explore which linguistic factors -- at the sentence and token level -- play an important role in influencing language model predictions, and investigate whether these are reflective of results found in humans and human corpora (Gries and Kootstra, 2017). We make use of the structural priming paradigm, where recent exposure to a structure facilitates processing of the same structure. We don't only investigate whether, but also where priming effects occur, and what factors predict them. We show that these effects can be explained via the inverse frequency effect, known in human priming, where rarer elements within a prime increase priming effects, as well as lexical dependence between prime and target. Our results provide an important piece in the puzzle of understanding how properties within their context affect structural prediction in language models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
