This paper investigates whether monolingual and multilingual LLMs show human-like preferences when presented with examples of relative clause attachment ambiguities in Italian and English. We also test whether these preferences can be modulated by lexical factors (the type of verb/noun in the matrix clause) which have been shown to be tied to subtle constraints on syntactic and semantic relations. Our results overall showcase how LLM behavior varies inconsistently across models and languages, and highlight the importance of leveraging subtle syntactic contrasts in exploring these models’ ability to correctly align with human-like preferences.