发表机构
University of Milano-Bicocca（米兰-比科卡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过意大利语伪词实验发现，大型语言模型对亚词汇线索的敏感性低于人类和fastText，表明其伪词处理机制与人类存在差异。
AI 中文摘要
系统性，即形式到意义的概率映射，渗透于语言的各个层面，且已有研究表明亚词汇线索支配着人类的伪词处理。然而，大型语言模型（LLMs）是否对这些线索表现出相当的敏感性仍不清楚。我们在两项意大利语二选一强制选择伪词实验中测试了五个LLM，并将其反应与人类行为基线进行了比较。当真实词选项提供词汇熟悉性线索时，LLM与人类的一致性比仅在伪词条件下更为可靠；在伪词仅条件下，LLM的表现大幅低于字符n-gram模型fastText。此外，可靠驱动人类与fastText一致的亚词汇余弦相似性线索并未持续转化为人类与LLM的一致性，且推理令牌消耗与人类处理难度无一致关系。这些发现表明，LLM不一定共享支配人类伪词处理的亚词汇线索；我们讨论了分词和训练数据覆盖作为候选解释。
英文摘要
Systematicity, the probabilistic mapping of form to meaning, permeates language at all levels, and sublexical cues have been shown to govern human pseudoword processing. Yet whether LLMs exhibit comparable sensitivity to these cues remains unclear. We tested five LLMs on two Italian two-alternative forced-choice pseudoword experiments and compared their responses with a human behavioural baseline. LLMs aligned more reliably with humans when real-word options provided a lexical familiarity cue than in the pseudoword-only condition, where they fell substantially below fastText, a character-n-gram model. In addition, the sublexical cosine-similarity cue that reliably drove human--fastText agreement did not consistently transfer to human--LLM alignment, and reasoning-token expenditure bore no consistent relation to human processing difficulty. These findings suggest that LLMs do not necessarily share the sublexical cues that govern human pseudoword processing; we discuss tokenization and training-data coverage as candidate explanations.
