English
Related papers

Related papers: Mechanistic Interpretability for Transformer-based…

200 papers

In this work, we introduce metrics to evaluate the use of simplified time series in the context of interpretability of a TSC -- a Time Series Classifier. Such simplifications are important because time series data, in contrast to text and…

Machine Learning · Computer Science 2025-11-04 Brigt Håvardstun , Felix Marti-Perez , Cèsar Ferri , Jan Arne Telle

Supervised learning of time series data has been extensively studied for the case of a categorical target variable. In some application domains, e.g., energy, environment and health monitoring, it occurs that the target variable is…

Machine Learning · Computer Science 2021-05-11 Dominique Gay , Alexis Bondu , Vincent Lemaire , Marc Boullé

Mechanistic interpretability improves the safety, reliability, and robustness of large AI models. This study examined individual attention heads in vision transformers (ViTs) fine tuned on distorted 2D spectrogram images containing non…

Machine Learning · Computer Science 2025-03-25 Nooshin Bahador

Transformer models have become a promising approach for crop-type classification. Although their attention weights can be used to understand the relevant time points for crop disambiguation, the validity of these insights depends on how…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Ivica Obadic , Ribana Roscher , Dario Augusto Borges Oliveira , Xiao Xiang Zhu

In this paper, we present a novel framework for enhancing model interpretability by integrating heatmaps produced separately by ResNet and a restructured 2D Transformer with globally weighted input saliency. We address the critical problem…

Machine Learning · Computer Science 2025-07-02 Jiztom Kavalakkatt Francis , Matthew J Darr

We present causal head gating (CHG), a scalable method for interpreting the functional roles of attention heads in transformer models. CHG learns soft gates over heads and assigns them a causal taxonomy - facilitating, interfering, or…

Artificial Intelligence · Computer Science 2025-10-27 Andrew Nam , Henry Conklin , Yukang Yang , Thomas Griffiths , Jonathan Cohen , Sarah-Jane Leslie

Transparency of neural networks' internal reasoning is at the heart of interpretability research, adding to trust, safety, and understanding of these models. The field of mechanistic interpretability has recently focused on studying…

Artificial Intelligence · Computer Science 2026-04-17 Nina Żukowska , Wolfgang Stammer , Bernt Schiele , Jonas Fischer

Sequence classification is the task of predicting a class label given a sequence of observations. In many applications such as healthcare monitoring or intrusion detection, early classification is crucial to prompt intervention. In this…

Machine Learning · Computer Science 2020-10-07 Maayan Shvo , Andrew C. Li , Rodrigo Toro Icarte , Sheila A. McIlraith

Rapid progress in machine learning and deep learning has enabled a wide range of applications in the electricity load forecasting of power systems, for instance, univariate and multivariate short-term load forecasting. Though the strong…

Machine Learning · Computer Science 2024-02-20 Yuqi Jiang , Yan Li , Yize Chen

This paper proposes a general interpretable predictive system with shared information. The system is able to perform predictions in a multi-task setting where distinct tasks are not bound to have the same input/output structure. Embeddings…

Machine Learning · Computer Science 2024-07-02 Maciej Żelaszczyk , Jacek Mańdziuk

Explainability is a topic of growing importance in NLP. In this work, we provide a unified perspective of explainability as a communication problem between an explainer and a layperson about a classifier's decision. We use this framework to…

Computation and Language · Computer Science 2020-10-13 Marcos V. Treviso , André F. T. Martins

Learning algorithms become more powerful, often at the cost of increased complexity. In response, the demand for algorithms to be transparent is growing. In NLP tasks, attention distributions learned by attention-based deep learning models…

Computation and Language · Computer Science 2019-07-09 Joris Baan , Maartje ter Hoeve , Marlies van der Wees , Anne Schuth , Maarten de Rijke

Transformer-based models have shown strong performance in time-series forecasting by leveraging self-attention to model long-range temporal dependencies. However, their effectiveness depends critically on the quality and structure of input…

Machine Learning · Computer Science 2026-02-11 Saurish Nagrath , Saroj Kumar Panigrahy

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Martina G. Vilas , Timothy Schaumlöffel , Gemma Roig

Machine learning methods are emerging as a universal paradigm for constructing correlative structure-property relationships in materials science based on multimodal characterization. However, this necessitates development of methods for…

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Lorenzo Basile , Valentino Maiorca , Diego Doimo , Francesco Locatello , Alberto Cazzaniga

Recent research in mechanistic interpretability has attempted to reverse-engineer Transformer models by carefully inspecting network weights and activations. However, these approaches require considerable manual effort and still fall short…

Machine Learning · Computer Science 2023-11-01 Dan Friedman , Alexander Wettig , Danqi Chen

We reveal that transformers trained in an autoregressive manner naturally encode time-delayed causal structures in their learned representations. When predicting future values in multivariate time series, the gradient sensitivities of…

Machine Learning · Computer Science 2026-01-12 Xinyue Wang , Stephen Wang , Biwei Huang

Transformers are increasingly adopted for modeling and forecasting time-series, yet their internal mechanisms remain poorly understood from a dynamical systems perspective. In contrast to classical autoregressive and state-space models,…

Machine Learning · Computer Science 2025-12-25 Gregory Duthé , Nikolaos Evangelou , Wei Liu , Ioannis G. Kevrekidis , Eleni Chatzi

Transformer architecture has widespread applications, particularly in Natural Language Processing and computer vision. Recently Transformers have been employed in various aspects of time-series analysis. This tutorial provides an overview…

Machine Learning · Computer Science 2023-07-27 Sabeen Ahmed , Ian E. Nielsen , Aakash Tripathi , Shamoon Siddiqui , Ghulam Rasool , Ravi P. Ramachandran