OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

2025 article liu2025olmotrace ○ Not yet verified

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

BibTeX

Local Entry

@article{liu2025olmotrace,
  title = {OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens},
  author = {Liu, Jiacheng and Blanton, Taylor and Elazar, Yanai and Min, Sewon and Chen, YenSung and Chheda-Kothary, Arnavi and Tran, Huy and Bischoff, Byron and Marsh, Eric and Schmitz, Michael and others},
  year = {2025},
  journal = {arXiv preprint arXiv:2504.07096},
  url = {https://arxiv.org/abs/2504.07096}
}

From OPENALEX

@article{liu2025olmotrace,
  title = {OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens},
  author = {Jiacheng Liu and Thomas N. Blanton and Sewon Min and Arnavi Chheda-Kothary and Huy Tran and Eric Marsh and Cassidy Trier and John T. James and Jon Borchardt and Evie Yu-Yen Cheng and Karen Farley and Sruthi Sreeram and Thomas Anderson and David Albright and Pang Wei Koh and Yejin Choi and Hannaneh Hajishirzi and Ali Farhadi},
  year = {2025},
  journal = {arXiv (Cornell University)},
  doi = {10.48550/arxiv.2504.07096}
}