AI translation of literary texts is "fine", but readers still prefer human translations
Paper • 2606.26040 • Published • 6
AI & ML interests
None defined yet.
Recent Activity
View all activity
marzena
authored 5
papers about 1 month ago
Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation
Paper • 2406.11580 • Published
AI use in American newspapers is widespread, uneven, and rarely disclosed
Paper • 2510.18774 • Published • 1
CaLMQA: Exploring culturally specific long-form question answering across 23 languages
Paper • 2406.17761 • Published
OverThink: Slowdown Attacks on Reasoning LLMs
Paper • 2502.02542 • Published
marzena
authored a
paper over 1 year ago
marzena
authored 3
papers over 2 years ago
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Paper • 2303.13408 • Published
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order
Paper • 2404.00399 • Published • 42
FABLES: Evaluating faithfulness and content selection in book-length summarization
Paper • 2404.01261 • Published • 3