Do Large Language Models Speak Alike? A Corpus-Based Analysis of Linguistic Similarity Across Generative AI Systems

Supplementary materials for the study “Do Large Language Models Speak Alike? A Corpus-Based Analysis of Linguistic Similarity Across Generative AI Systems” The supplementary archive contains eight Excel files providing the data and analytical results underlying the study, including lexical similarity, syntactic similarity, mean dependency distance (MDD), within-model similarity, across-model similarity, and related analyses of the linguistic similarity of responses generated by ChatGPT, Gemini, and Llama.