all AI news
Watermarking Makes Language Models Radioactive
Feb. 26, 2024, 5:42 a.m. | Tom Sander, Pierre Fernandez, Alain Durmus, Matthijs Douze, Teddy Furon
cs.LG updates on arXiv.org arxiv.org
Abstract: This paper investigates the radioactivity of LLM-generated texts, i.e. whether it is possible to detect that such input was used as training data. Conventional methods like membership inference can carry out this detection with some level of accuracy. We show that watermarked training data leaves traces easier to detect and much more reliable than membership inference. We link the contamination level to the watermark robustness, its proportion in the training set, and the fine-tuning process. …
abstract accuracy arxiv cs.ai cs.cl cs.cr cs.lg data detection generated inference language language models llm paper show traces training training data type watermarking
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
.NET Software Engineer (AI Focus)
@ Boskalis | Papendrecht, Netherlands