English
Related papers

Related papers: Dissecting Jet-Tagger Through Mechanistic Interpre…

200 papers

Mechanistic interpretability has identified small sets of attention heads that implement specific behaviours in transformer language models, but recovering these circuits typically requires a bespoke analytical pipeline for each new task.…

Machine Learning · Computer Science 2026-05-27 Barsat Khadka

Machine learning (ML) algorithms, particularly attention-based transformer models, have become indispensable for analyzing the vast data generated by particle physics experiments like ATLAS and CMS at the CERN LHC. Particle Transformer…

High Energy Physics - Phenomenology · Physics 2024-12-10 Aaron Wang , Abhijith Gandrakota , Jennifer Ngadiuba , Vivekanand Sahu , Priyansh Bhatnagar , Elham E Khoda , Javier Duarte

At the CERN LHC, the task of jet tagging, whose goal is to infer the origin of a jet given a set of final-state particles, is dominated by machine learning methods. Graph neural networks have been used to address this task by treating jets…

High Energy Physics - Experiment · Physics 2022-11-21 Farouk Mokhtar , Raghav Kansal , Javier Duarte

Classification of jets with deep learning has gained significant attention in recent times. However, the performance of deep neural networks is often achieved at the cost of interpretability. Here we propose an interpretable network trained…

High Energy Physics - Phenomenology · Physics 2020-03-27 Amit Chakraborty , Sung Hak Lim , Mihoko M. Nojiri

Transformer-based language models exhibit complex and distributed behavior, yet their internal computations remain poorly understood. Existing mechanistic interpretability methods typically treat attention heads and multilayer perceptron…

Machine Learning · Computer Science 2025-11-26 Areeb Ahmad , Abhinav Joshi , Ashutosh Modi

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

Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their internal decision-making challenging. Existing…

Machine Learning · Computer Science 2025-11-27 Matīss Kalnāre , Sofoklis Kitharidis , Thomas Bäck , Niki van Stein

Understanding AI systems' inner workings is critical for ensuring value alignment and safety. This review explores mechanistic interpretability: reverse engineering the computational mechanisms and representations learned by neural networks…

Artificial Intelligence · Computer Science 2024-08-27 Leonard Bereska , Efstratios Gavves

Graph neural networks such as ParticleNet and transformer based networks on point clouds such as ParticleTransformer achieve state-of-the-art performance on jet tagging benchmarks at the Large Hadron Collider, yet the physical reasoning…

High Energy Physics - Phenomenology · Physics 2026-04-29 Pahal D. Patel , Sanmay Ganguly

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…

Machine Learning · Computer Science 2026-05-12 Ward Gauderis , Thomas Dooms , Steven T. Holmer , Kola Ayonrinde , Geraint A. Wiggins

Mechanistic interpretability aims to reverse-engineer transformer computations by identifying causal circuits through activation patching. However, scaling these interventions across diverse prompts and task families produces…

Artificial Intelligence · Computer Science 2026-05-08 Ruben Fernandez-Boullon , David N. Olivieri

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

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

Recent developments in the methods of explainable AI (XAI) allow researchers to explore the inner workings of deep neural networks (DNNs), revealing crucial information about input-output relationships and realizing how data connects with…

High Energy Physics - Experiment · Physics 2023-07-07 Ayush Khot , Mark S. Neubauer , Avik Roy

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-based language models are treated as black-boxes because of their large number of parameters and complex internal interactions, which is a serious safety concern. Mechanistic Interpretability (MI) intends to reverse-engineer…

Machine Learning · Computer Science 2024-05-08 Jorge García-Carrasco , Alejandro Maté , Juan Trujillo

As AI systems are used in high-stakes applications, ensuring interpretability is crucial. Mechanistic Interpretability (MI) aims to reverse-engineer neural networks by extracting human-understandable algorithms to explain their behavior.…

Machine Learning · Computer Science 2025-03-03 Maxime Méloux , Silviu Maniu , François Portet , Maxime Peyrard

Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…

Machine Learning · Computer Science 2026-03-16 Harshwardhan Fartale , Ashish Kattamuri , Rahul Raja , Arpita Vats , Ishita Prasad , Akshata Kishore Moharir

Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for…

Artificial Intelligence · Computer Science 2025-10-14 Daking Rai , Yilun Zhou , Shi Feng , Abulhair Saparov , Ziyu Yao

Real-time jet tagging is critical for identifying short-lived particle decays in the high-throughput detectors of the Large Hadron Collider, where real-time trigger systems responsible for deciding which collision events to store impose…

High Energy Physics - Experiment · Physics 2026-05-22 Aaron Wang , Zihan Zhao , Alan Xia , Chang Sun , Abhijith Gandrakota , Jennifer Ngadiuba , Richard Cavanaugh , Javier Duarte
‹ Prev 1 2 3 10 Next ›