Andrea Nini on Mythryl: “Well-known #forensic #linguistics cases involved impersonation, e.g…”

Well-known #forensic #linguistics cases involved impersonation, e.g. murderer pretending to be the victim in text messages. In a new preprint with Baoyi Zeng we show that #LLMs can't fool authorship verification methods via prompting alone. Paper on arXiv: https://arxiv.org/abs/2603.29454

andreanini.comNew pre-print: “Authorship Impersonation via LLM Prompting does not Evade Authorship Verification Methods”I'm pleased to announce the pre-print of a new article on LLM impersonation, with Baoyi Zeng as first author. The paper shows that current state-of-the-art authorship verification methods tend not to be fooled by an LLM trying to impersonate someone simply using prompting. Several high profile forensic linguistic cases involved the perpetrator manually trying to impersonate someone, such as the victim.

1/4/26, 12:17 pm3 reposts10 likes

Post