OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens
Authors
Liu, Jiacheng, Blanton, Taylor, Elazar, Yanai, Min, Sewon, Chen, YenSung, Chheda-Kothary, Arnavi, Tran, Huy, Bischoff, Byron, Marsh, Eric, Schmitz, Michael, others
Venue
arXiv preprint arXiv:2504.07096