@inproceedings{liu-etal-2025-olmotrace,
    title = "{OLM}o{T}race: Tracing Language Model Outputs Back to Trillions of Training Tokens",
    author = "Liu, Jiacheng  and
      Blanton, Taylor  and
      Elazar, Yanai  and
      Min, Sewon  and
      Chen, Yen-Sung  and
      Chheda-Kothary, Arnavi  and
      Tran, Huy  and
      Bischoff, Byron  and
      Marsh, Eric  and
      Schmitz, Michael  and
      Trier, Cassidy  and
      Sarnat, Aaron  and
      James, Jenna  and
      Borchardt, Jon  and
      Kuehl, Bailey  and
      Cheng, Evie Yu-Yen  and
      Farley, Karen  and
      Anderson, Taira  and
      Albright, David  and
      Schoenick, Carissa  and
      Soldaini, Luca  and
      Groeneveld, Dirk  and
      Pang, Rock Yuren  and
      Koh, Pang Wei  and
      Smith, Noah A.  and
      Lebrecht, Sophie  and
      Choi, Yejin  and
      Hajishirzi, Hannaneh  and
      Farhadi, Ali  and
      Dodge, Jesse",
    editor = "Mishra, Pushkar  and
      Muresan, Smaranda  and
      Yu, Tao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-demo.18/",
    pages = "178--188",
    ISBN = "979-8-89176-253-4",
    abstract = "We present OLMoTrace, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMoTrace finds and shows verbatim matches between segments of language model output and documents in the training text corpora. Powered by an extended version of infini-gram (Liu et al., 2024), our system returns tracing results within a few seconds. OLMoTrace can help users understand the behavior of language models through the lens of their training data. We showcase how it can be used to explore fact checking, hallucination, and the creativity of language models. OLMoTrace is publicly available and fully open-source."
}