Pré-Publication, Document De Travail Année : 2025

Interpreto: An Explainability Library for Transformers

Frédéric Boisnard

Résumé

Interpreto is a Python library for post-hoc explainability of text HuggingFace models, from early BERT variants to LLMs. It provides two complementary families of methods: attributions and concept-based explanations. The library connects recent research to practical tooling for data scientists, aiming to make explanations accessible to end users. It includes documentation, examples, and tutorials. Interpreto supports both classification and generation models through a unified API. A key differentiator is its concept-based functionality, which goes beyond feature-level attributions and is uncommon in existing libraries. The library is open source; install via pip install interpreto. Code and documentation are available at https://github.com/FOR-sight-ai/interpreto.

Fichier principal
Vignette du fichier
2512.09730v1.pdf (591.04 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-05411956 , version 1 (11-12-2025)

Licence

Identifiants

Citer

Antonin Poché, Thomas Mullor, Gabriele Sarti, Frédéric Boisnard, Corentin Friedrich, et al.. Interpreto: An Explainability Library for Transformers. 2025. ⟨hal-05411956⟩
948 Consultations
239 Téléchargements

Altmetric

Partager

  • More