A systematic benchmark of multilingual authorship attribution shows fine-tuned LLM detectors exceed 0.9 macro F1 in-language but transfer poorly across languages, with Russian training generalizing better than English.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Authorship Attribution in Multilingual Machine-Generated Texts
A systematic benchmark of multilingual authorship attribution shows fine-tuned LLM detectors exceed 0.9 macro F1 in-language but transfer poorly across languages, with Russian training generalizing better than English.