paper-with-me

Papers

The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning

2026-02-27 · Jonathan Drechsel, Steffen Herbold arxiv

We present gradiend, an open-source Python package that operationalizes the GRADIEND method for learning feature directions from factual-counterfactual MLM and CLM gradients in language models. The package provides a unified workflow for feature-related data creation, training, evaluation, visualization, persistent model rewriting via controlled weight updates, and multi-feature comparison. We demonstrate GRADIEND on an English pronoun paradigm and on a large-scale feature comparison that reproduces prior use cases.

📄 PDF Abstract BibTeX arXiv:2602.23993

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GRADIEND: Monosemantic Feature Learning within Neural Networks Applied to Gender Debiasing of Transformer Models

2025-02-03 · Jonathan Drechsel, Steffen Herbold

AI systems frequently exhibit and amplify social biases, including gender bias, leading to harmful consequences in critical areas. This study introduces a novel encoder-decoder approach that leverages model gradients to …

Decoder

path_boost: A Python Package for Interpretable Graph-Level Prediction using Path-Based Gradient Boosting

2026-07-08 · Claudio Meggio, Johan Pensar, Riccardo De Bin arxiv

We present path_boost, a Python package for interpretable supervised learning on graph-structured input data. The package implements PathBoost, a gradient boosting algorithm that automatically discovers predictive labele…

Molecular Property PredictionBinary ClassificationGraph Neural Network

libact: Pool-based Active Learning in Python

2017-10-01 · Yao-Yuan Yang, Shao-Chuan Lee, Yu-An Chung, Tung-En Wu 외

libact is a Python package designed to make active learning easier for general users. The package not only implements several popular active learning strategies, but also features the active-learning-by-learning meta-alg…

Active Learning

Tangent: Automatic Differentiation Using Source Code Transformation in Python

2017-11-07 · Bart van Merriënboer, Alexander B. Wiltschko, Dan Moldovan

Automatic differentiation (AD) is an essential primitive for machine learning programming systems. Tangent is a new library that performs AD using source code transformation (SCT) in Python. It takes numeric functions wr…

BIG-bench Machine Learning

TextDescriptives: A Python package for calculating a large variety of metrics from text

2023-01-05 · Lasse Hansen, Ludvig Renbo Olsen, Kenneth Enevoldsen

TextDescriptives is a Python package for calculating a large variety of metrics from text. It is built on top of spaCy and can be easily integrated into existing workflows. The package has already been used for analysing…