Interpreto: An Explainability Library for Transformers
Antonin Poché Institut de Recherche en Informatique de Toulouse and IRT Saint Exupery, Thomas Mullor INSTITUTE OF TECHNOLOGICAL RESEARCH IRT SAINT EXUPERY, Gabriele Sarti, Frédéric Boisnard INSTITUTE OF TECHNOLOGICAL RESEARCH IRT SAINT EXUPERY, Corentin Friedrich IRT Saint Exupéry, Charlotte Claye Centrale Supélec, Francois Hoofd IRT SAINT EXUPERY, Raphael Bernas 等 11 位作者
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.
尚无 AI 解读，展示原文摘要
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表