大语言模型在短语顺序偏好上与人类高度相似，揭示其语言处理机制的类人特征。
Language Models Largely Exhibit Human-like Constituent Ordering Preferences
- 对比多种大模型，测试其对四类短语移动的偏好
- 除介词短语移动外，多数任务表现接近人类水平
- 为理解模型如何处理语言结构提供新视角
尽管英语句子的词序通常固定，但短语成分的顺序却有较大灵活性。一种主流理论认为，短语顺序与其权重（长度或复杂度）直接相关。这一理论在自然语言处理领域具有重要意义：尽管大语言模型（LLMs）近年取得显著进展，但其语言处理机制仍不明确，且与人类处理方式的异同尚不清楚。本文比较了多种具有不同特性的大语言模型，评估其在四类短语移动任务中的表现：重名词短语前移、小品词移动、与格交替及多个介词短语排列。结果显示，尽管在小品词移动任务中表现意外不佳，大语言模型整体上仍与人类对短语顺序的偏好高度一致。
原文摘要 · Abstract (English)
Though English sentences are typically inflexible vis-à-vis word order, constituents often show far more variability in ordering. One prominent theory presents the notion that constituent ordering is directly correlated with constituent weight: a measure of the constituent's length or complexity. Such theories are interesting in the context of natural language processing (NLP), because while recent advances in NLP have led to significant gains in the performance of large language models (LLMs), much remains unclear about how these models process language, and how this compares to human language processing. In particular, the question remains whether LLMs display the same patterns with constituent movement, and may provide insights into existing theories on when and how the shift occurs in human language. We compare a variety of LLMs with diverse properties to evaluate broad LLM performance on four types of constituent movement: heavy NP shift, particle movement, dative alternation, and multiple PPs. Despite performing unexpectedly around particle movement, LLMs generally align with human preferences around constituent ordering.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。