Interpreto: An Explainability Library for Transformers

• URL: http://arxiv.org/abs/2512.09730v1
• Date: Wed, 10 Dec 2025 15:12:09 GMT
• Title: Interpreto: An Explainability Library for Transformers
• Authors: Antonin Poché, Thomas Mullor, Gabriele Sarti, Frédéric Boisnard, Corentin Friedrich, Charlotte Claye, François Hoofd, Raphael Bernas, Céline Hudelot, Fanny Jourdan,
• Abstract summary: Interpreto is a Python library for post-hoc explainability of text HuggingFace models.<n>It provides two complementary families of methods: attributions and concept-based explanations.
• Score: 7.728781113727994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• PyPulse: A Python Library for Biosignal Imputation [58.35269251730328]
  We introduce PyPulse, a Python package for imputation of biosignals in both clinical and wearable sensor settings.<n>PyPulse's framework provides a modular and extendable framework with high ease-of-use for a broad userbase, including non-machine-learning bioresearchers.<n>We released PyPulse under the MIT License on Github and PyPI.
  arXiv  Detail & Related papers  (2024-12-09T11:00:55Z)
• pyvene: A Library for Understanding and Improving PyTorch Models via Interventions [79.72930339711478]
  $textbfpyvene$ is an open-source library that supports customizable interventions on a range of different PyTorch modules. We show how $textbfpyvene$ provides a unified framework for performing interventions on neural models and sharing the intervened upon models with others.
  arXiv  Detail & Related papers  (2024-03-12T16:46:54Z)
• TrueLearn: A Python Library for Personalised Informational Recommendations with (Implicit) Feedback [4.575111313202425]
  This work describes the TrueLearn Python library, which contains a family of online learning Bayesian models. For the sake of interpretability and putting the user in control, the TrueLearn library also contains different representations to help end-users visualise the learner models.
  arXiv  Detail & Related papers  (2023-09-20T07:21:50Z)
• Causal-learn: Causal Discovery in Python [53.17423883919072]
  Causal discovery aims at revealing causal relations from observational data. $textitcausal-learn$ is an open-source Python library for causal discovery.
  arXiv  Detail & Related papers  (2023-07-31T05:00:35Z)
• SequeL: A Continual Learning Library in PyTorch and JAX [50.33956216274694]
  SequeL is a library for Continual Learning that supports both PyTorch and JAX frameworks. It provides a unified interface for a wide range of Continual Learning algorithms, including regularization-based approaches, replay-based approaches, and hybrid approaches. We release SequeL as an open-source library, enabling researchers and developers to easily experiment and extend the library for their own purposes.
  arXiv  Detail & Related papers  (2023-04-21T10:00:22Z)
• PyTorch Adapt [37.03614011735927]
  PyTorch Adapt is a library for domain adaptation. domain adaptation is a type of machine learning algorithm that re-purposes existing models to work in new domains. It is a fully-featured toolkit, allowing users to create a complete train/test pipeline in a few lines of code.
  arXiv  Detail & Related papers  (2022-11-28T18:59:09Z)
• scikit-fda: A Python Package for Functional Data Analysis [0.0]
  scikit-fda is a Python package for Functional Data Analysis (FDA) It provides a comprehensive set of tools for representation, preprocessing, and exploratory analysis of functional data.
  arXiv  Detail & Related papers  (2022-11-04T16:34:03Z)
• DocCoder: Generating Code by Retrieving and Reading Docs [87.88474546826913]
  We introduce DocCoder, an approach that explicitly leverages code manuals and documentation. Our approach is general, can be applied to any programming language, and is agnostic to the underlying neural model.
  arXiv  Detail & Related papers  (2022-07-13T06:47:51Z)
• OmniXAI: A Library for Explainable AI [98.07381528393245]
  We introduce OmniXAI, an open-source Python library of eXplainable AI (XAI) It offers omni-way explainable AI capabilities and various interpretable machine learning techniques. For practitioners, the library provides an easy-to-use unified interface to generate the explanations for their applications.
  arXiv  Detail & Related papers  (2022-06-01T11:35:37Z)
• PyGOD: A Python Library for Graph Outlier Detection [56.33769221859135]
  PyGOD is an open-source library for detecting outliers in graph data. It supports a wide array of leading graph-based methods for outlier detection. PyGOD is released under a BSD 2-Clause license at https://pygod.org and at the Python Package Index (PyPI)
  arXiv  Detail & Related papers  (2022-04-26T06:15:21Z)
• Small-Text: Active Learning for Text Classification in Python [23.87081733039124]
  small-text is an easy-to-use active learning library for Python. It offers pool-based active learning for single- and multi-label text classification.
  arXiv  Detail & Related papers  (2021-07-21T19:23:56Z)
• LENs: a Python library for Logic Explained Networks [2.064612766965483]
  LENs is a Python module integrating a variety of state-of-the-art approaches to provide logic explanations from neural networks. LENs is distributed under the Apache 2.0 licence allowing both academic and commercial use.
  arXiv  Detail & Related papers  (2021-05-25T06:41:54Z)
• giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration [4.8353738137338755]
  giotto-tda is a Python library that integrates high-performance topological data analysis with machine learning. The library's ability to handle various types of data is rooted in a wide range of preprocessing techniques.
  arXiv  Detail & Related papers  (2020-04-06T10:53:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.