Answers are grounded in this paper and cite their sources.
This analysis reveals that AI generated texts show distinct vocabulary patterns compared to human texts, suggesting limitations in emulation abilities.
AI generated texts seem human-written and having a similar quality to that of texts produced by humans. The etymologic analysis of the vocabulary of texts is proposed for examining the complexity of AI generated texts. The etymologic analysis shows that, when asked to emulate an author, AI appears to use an etymologic mixture of the vocabulary less complex than that of the human literary texts. When asked to recount a specific literary work emulating its author, AI produced writings with an etymologic distribution far from that of the narrated text and with aberrations, throwing doubt on AI ability of emulating a specific author at the etymologic level. The tool of etymologic analysis may help distinguish between AI and human generated texts.
No takes yet. Share an insight, caveat, or question.
Teodorescu et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: