@inproceedings{poche-etal-2026-interpreto,
    title = "Interpreto: An Explainability Library for Transformers",
    author = "Poch{\'e}, Antonin  and
      Mullor, Thomas  and
      Sarti, Gabriele  and
      Boisnard, Fr{\'e}d{\'e}ric  and
      Friedrich, Corentin  and
      Claye, Charlotte  and
      Hoofd, Francois  and
      Bernas, Raphael  and
      Asher, Nicholas  and
      Hudelot, Celine  and
      Jourdan, Fanny",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.1/",
    pages = "1--13",
    ISBN = "979-8-89176-392-0",
    abstract = "Interpreto is an open-source Python library for interpreting HuggingFace language models, from early BERT variants to LLMs. It provides two complementary families of methods: attribution methods and concept-based explanations. The library bridges recent research and practical tooling by exposing explanation workflows through a unified API for both classification and text generation. A key differentiator is its end-to-end concept-based pipeline (from activation extraction to concept learning, interpretation, and scoring), which goes beyond feature-level attributions and is uncommon in existing libraries."
}