作者位次 #6/11ACL 2026Workshop· ACL System Demonstrations
Interpreto: An Explainability Library for Transformers
Antonin Poché · Thomas Mullor · Gabriele Sarti · Frédéric Boisnard · Corentin Friedrich · Charlotte Claye · Francois Hoofd · Raphael Bernas · Nicholas Asher · Céline Hudelot · Fanny Jourdan
摘要
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...