English
Related papers

Related papers: Mechanistic Interpretability for Transformer-based…

200 papers

While artificial neural networks excel in unsupervised learning of non-sparse structure, classical statistical regression techniques offer better interpretability, in particular when sparseness is enforced by $\ell_1$ regularization,…

Mechanistic interpretability often uses activation patching, causal tracing, path patching, and steering directions to reveal behaviorally meaningful directions in Transformer activation space. This paper develops a field-theoretic…

Machine Learning · Computer Science 2026-05-26 David N. Olivieri , Antonio F. Pérez Rodríguez

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

Brain-to-speech decoding models demonstrate robust performance in vocalized, mimed, and imagined speech; yet, the fundamental mechanisms via which these models capture and transmit information across different speech modalities are less…

Machine Learning · Computer Science 2026-02-03 Maryam Maghsoudi , Ayushi Mishra

Transformer-based time series forecasting has recently gained strong interest due to the ability of transformers to model sequential data. Most of the state-of-the-art architectures exploit either temporal or inter-channel dependencies,…

Machine Learning · Computer Science 2025-03-25 Davide Villaboni , Alberto Castellini , Ivan Luciano Danesi , Alessandro Farinelli

The present study explores the interpretability of latent spaces produced by time series foundation models, focusing on their potential for visual analysis tasks. Specifically, we evaluate the MOMENT family of models, a set of…

In many scientific problems such as video surveillance, modern genomics, and finance, data are often collected from diverse measurements across time that exhibit time-dependent heterogeneous properties. Thus, it is important to not only…

Machine Learning · Statistics 2022-10-10 Lin Qiu , Vernon M. Chinchilli , Lin Lin

This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various…

Computer Vision and Pattern Recognition · Computer Science 2018-06-25 Phongtharin Vinayavekhin , Subhajit Chaudhury , Asim Munawar , Don Joven Agravante , Giovanni De Magistris , Daiki Kimura , Ryuki Tachibana

Mechanistic interpretability aims to understand model behaviors in terms of specific, interpretable features, often hypothesized to manifest as low-dimensional subspaces of activations. Specifically, recent studies have explored subspace…

Machine Learning · Computer Science 2023-12-07 Aleksandar Makelov , Georg Lange , Neel Nanda

Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond. This work provides a theoretical analysis of the…

Machine Learning · Computer Science 2022-06-27 Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Cyril Zhang

Mechanistic interpretability has transformed the analysis of transformer circuits by decomposing model behavior into competing algorithms, identifying phase transitions during training, and deriving closed-form predictions for when and why…

Machine Learning · Computer Science 2026-03-19 Alma Lago

Deep neural perception and control networks are likely to be a key component of self-driving vehicles. These models need to be explainable - they should provide easy-to-interpret rationales for their behavior - so that passengers, insurance…

Computer Vision and Pattern Recognition · Computer Science 2017-04-03 Jinkyu Kim , John Canny

Exploratory analysis of time series data can yield a better understanding of complex dynamical systems. Granger causality is a practical framework for analysing interactions in sequential data, applied in a wide range of domains. In this…

Machine Learning · Computer Science 2021-01-20 Ričards Marcinkevičs , Julia E. Vogt

Mechanistic Interpretability (MI) aims to reverse-engineer model behaviors by identifying functional sub-networks. Yet, the scientific validity of these findings depends on their stability. In this work, we argue that circuit discovery is…

Machine Learning · Computer Science 2026-02-04 Maxime Méloux , François Portet , Maxime Peyrard

Predictive process monitoring aims to support the execution of a process during runtime with various predictions about the further evolution of a process instance. In the last years a plethora of deep learning architectures have been…

Machine Learning · Computer Science 2024-08-15 Martin Käppel , Lars Ackermann , Stefan Jablonski , Simon Härtl

Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed. First, researchers choose a…

Machine Learning · Computer Science 2023-10-31 Arthur Conmy , Augustine N. Mavor-Parker , Aengus Lynch , Stefan Heimersheim , Adrià Garriga-Alonso

Discovering shapelets -- i.e., discriminative temporal patterns within time series -- has been widely studied to address the inherent complexity of time-series classification (TSC) and to make model decision-making processes more…

Machine Learning · Computer Science 2026-05-20 Seongjun Lee , Seokhyun Lee , Changhee Lee

Mechanistic interpretability aims to understand neural networks by identifying which learned features mediate specific behaviors. Attribution graphs reveal these feature pathways, but interpreting them requires extensive manual analysis --…

Computation and Language · Computer Science 2025-11-11 Giuseppe Birardi

Generative AI models offer powerful capabilities but often lack transparency, making it difficult to interpret their output. This is critical in cases involving artistic or copyrighted content. This work introduces a search-inspired…

Artificial Intelligence · Computer Science 2025-04-03 Theodoros Aivalis , Iraklis A. Klampanos , Antonis Troumpoukis , Joemon M. Jose

We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a…