{"ID":2830758,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.09730","arxiv_id":"2512.09730","title":"Interpreto: An Explainability Library for Transformers","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.","short_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 t...","url_abs":"https://arxiv.org/abs/2512.09730","url_pdf":"https://arxiv.org/pdf/2512.09730v2","authors":"[\"Antonin Poché\",\"Thomas Mullor\",\"Gabriele Sarti\",\"Frédéric Boisnard\",\"Corentin Friedrich\",\"Charlotte Claye\",\"François Hoofd\",\"Raphael Bernas\",\"Céline Hudelot\",\"Fanny Jourdan\"]","published":"2025-12-10T15:12:09Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Transformer\",\"Large Language Model\",\"Language Model\"]","has_code":false}