Interpreto: An Explainability Library for Transformers
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914622480580608 |
|---|---|
| author | Poché, Antonin Mullor, Thomas Sarti, Gabriele Boisnard, Frédéric Friedrich, Corentin Claye, Charlotte Hoofd, François Bernas, Raphael Asher, Nicholas Hudelot, Céline Jourdan, Fanny |
| author_facet | Poché, Antonin Mullor, Thomas Sarti, Gabriele Boisnard, Frédéric Friedrich, Corentin Claye, Charlotte Hoofd, François Bernas, Raphael Asher, Nicholas Hudelot, Céline Jourdan, Fanny |
| contents | 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. See GitHub: https://github.com/FOR-sight-ai/interpreto and the demo website: https://for-sight-ai.github.io/interpreto-demo/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09730 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interpreto: An Explainability Library for Transformers Poché, Antonin Mullor, Thomas Sarti, Gabriele Boisnard, Frédéric Friedrich, Corentin Claye, Charlotte Hoofd, François Bernas, Raphael Asher, Nicholas Hudelot, Céline Jourdan, Fanny Computation and Language Machine Learning I.2.7 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. See GitHub: https://github.com/FOR-sight-ai/interpreto and the demo website: https://for-sight-ai.github.io/interpreto-demo/. |
| title | Interpreto: An Explainability Library for Transformers |
| topic | Computation and Language Machine Learning I.2.7 |
| url | https://arxiv.org/abs/2512.09730 |