发表机构
University of Oxford（牛津大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究大语言模型是否像人类一样句法趋同，通过替换范式数据在多个模型测量CFG规则复用。发现各模型与前一轮人类话语规则重叠多，指令微调模型有特点，还在词汇和语义相似度上有表现，揭示了模型在句法复用方面与人类的异同。
AI 中文摘要
句法趋同是人类对话中一个有充分记录的特征，被广泛认为在意识层面之下运作。大语言模型是否相对于人类基线并在广泛的句法结构中表现出类似的句法趋同仍是一个开放问题。本研究使用替换范式数据，在16个开放权重的Llama和Gemma模型（1B - 70B，预训练和指令微调）的1901个匹配位置测量上下文无关语法（CFG）规则的相邻轮复用。每个模型与前一轮人类话语的CFG规则重叠都比与采样的不相关人类引导语更多，且低频规则的实际与随机差异更大。每个指令微调模型与实际引导语的自然输出重叠也比它所替换的人类回应更多。然而，相对于预训练变体，指令微调输出与不相关引导语重叠更多，实际与随机增量更小，且在目标规则集大小不变时条件规则复用几率更低。在探索性分析中，每个模型与前一轮的平均词汇和语义相似度都比匹配的人类回应更高。指令微调模型在所有八个架构对中产生的回应平均语义相似度也比其预训练对应模型更高，而词汇相似度结果更具异质性。
英文摘要
Syntactic convergence (the tendency of speakers to adapt in language towards the grammatical profiles of their interlocutors) is a well-documented feature of human dialogue widely considered to operate below conscious awareness. Whether large language models exhibit analogous syntactic convergence toward human users relative to human baselines and across a broad range of syntactic constructions remains an open question. Using substitution-paradigm data in which model generations replace one speaker's turns in pre-existing human dialogues, this study measures turn-adjacent reuse of context-free grammar (CFG) rules across sixteen open-weight Llama and Gemma models (1B-70B, pretrained and instruction-tuned) at 1,901 matched positions per model. Every model showed greater CFG-rule overlap with the preceding human turn than with a sampled unrelated human prime, and in every model this actual-versus-random difference was larger for lower-frequency rules. Each instruction-tuned model also showed greater natural-output overlap with the actual prime than the human response it replaced, and all eight matched architecture pairs exhibited greater actual-prime overlap after instruction tuning. However, relative to pretrained variants, instruction-tuned outputs overlapped more with unrelated primes, showed a smaller actual-versus-random increment, and had lower conditional rule-reuse odds once target rule-set size was held constant. In exploratory analyses, each model exhibited greater mean lexical and semantic similarity to the preceding turn than the matched human responses did. Instruction-tuned models additionally produced responses with greater mean semantic similarity than their pretrained counterparts in all eight architecture pairs, whereas the lexical similarity results were more heterogeneous.
