English
Related papers

Related papers: Better Explain Transformers by Illuminating Import…

200 papers

Transformer is the backbone of modern NLP models. In this paper, we propose RealFormer, a simple and generic technique to create Residual Attention Layer Transformer networks that significantly outperform the canonical Transformer and its…

Machine Learning · Computer Science 2021-09-14 Ruining He , Anirudh Ravula , Bhargav Kanagal , Joshua Ainslie

Locating and editing knowledge in large language models (LLMs) is crucial for enhancing their accuracy, safety, and inference rationale. We introduce ``concept editing'', an innovative variation of knowledge editing that uncovers…

Computation and Language · Computer Science 2024-08-23 Nura Aljaafari , Danilo S. Carvalho , André Freitas

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

Attending to what is relevant is fundamental to both the mammalian brain and modern machine learning models such as Transformers. Yet, determining relevance remains a core challenge, traditionally offloaded to learning algorithms like…

Machine Learning · Computer Science 2025-05-13 Ahsan Adeel

Convolutional neural networks (CNNs) underpin many modern computer vision systems. With applications ranging from common to critical areas, a need to explain and understand the model and its decisions (XAI) emerged. Prior works suggest that…

Computer Vision and Pattern Recognition · Computer Science 2025-11-05 Vojtěch Kůr , Adam Bajger , Adam Kukučka , Marek Hradil , Vít Musil , Tomáš Brázdil

Transformer language models are state of the art in a multitude of NLP tasks. Despite these successes, their opaqueness remains problematic. Recent methods aiming to provide interpretability and explainability to black-box models primarily…

Computation and Language · Computer Science 2022-03-14 Felix Friedrich , Patrick Schramowski , Christopher Tauchmann , Kristian Kersting

Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score using modified rules, rather than the gradient. We analyze…

Machine Learning · Computer Science 2024-02-20 Leon Sixt , Maximilian Granz , Tim Landgraf

This paper bridges the gap between mathematical heuristic strategies learned from Deep Reinforcement Learning (DRL) in automated agent negotiation, and comprehensible, natural language explanations. Our aim is to make these strategies more…

Artificial Intelligence · Computer Science 2023-11-27 Pallavi Bagga , Kostas Stathis

The self-attention module is a key component of Transformer-based models, wherein each token pays attention to every other token. Recent studies have shown that these heads exhibit syntactic, semantic, or local behaviour. Some studies have…

Computation and Language · Computer Science 2020-08-14 Madhura Pande , Aakriti Budhraja , Preksha Nema , Pratyush Kumar , Mitesh M. Khapra

The transparent formulation of explanation methods is essential for elucidating the predictions of neural networks, which are typically black-box models. Layer-wise Relevance Propagation (LRP) is a well-established method that transparently…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Seitaro Otsuki , Tsumugi Iida , Félix Doublet , Tsubasa Hirakawa , Takayoshi Yamashita , Hironobu Fujiyoshi , Komei Sugiura

Explainable AI (XAI) has become increasingly important with the rise of large transformer models, yet many explanation methods designed for CNNs transfer poorly to Vision Transformers (ViTs). Existing ViT explanations often rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-08 Meghna P Ayyar , Jenny Benois-Pineau , Akka Zemmari

Transformer encoders are widely deployed in large-scale web services for natural language understanding tasks such as text classification, semantic retrieval, and content ranking. However, their high inference latency and memory consumption…

Machine Learning · Computer Science 2025-12-25 Zeli Su , Ziyin Zhang , Wenzheng Zhang , Zhou Liu , Guixian Xu , Wentao Zhang

In recent years, artificial intelligence (AI) systems have come to the forefront. These systems, mostly based on Deep learning (DL), achieve excellent results in areas such as image processing, natural language processing, or speech…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Frantisek Sefcik , Wanda Benesova

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

Language models with the Transformers structure have shown great performance in natural language processing. However, there still poses problems when fine-tuning pre-trained language models on downstream tasks, such as over-fitting or…

Computation and Language · Computer Science 2023-05-12 Hongyi Yuan , Zheng Yuan , Chuanqi Tan , Fei Huang , Songfang Huang

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

Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them more human interpretable. In this paper, we investigate LM…

Computation and Language · Computer Science 2023-11-27 Shahar Katz , Yonatan Belinkov

Even though deep neural networks (DNNs) achieve state-of-the-art results for a number of problems involving genomic data, getting DNNs to explain their decision-making process has been a major challenge due to their black-box nature. One…

Genomics · Quantitative Biology 2022-12-14 Utku Ozbulak , Solha Kang , Jasper Zuallaert , Stephen Depuydt , Joris Vankerschaver

Distance-based classifiers, such as k-nearest neighbors and support vector machines, continue to be a workhorse of machine learning, widely used in science and industry. In practice, to derive insights from these models, it is also…

Machine Learning · Computer Science 2026-05-05 Florian Bley , Jacob Kauffmann , Simon León Krug , Klaus-Robert Müller , Grégoire Montavon

The use of convolutional neural networks (CNNs) for classification tasks has become dominant in various medical imaging applications. At the same time, recent advances in interpretable machine learning techniques have shown great potential…

Image and Video Processing · Electrical Eng. & Systems 2019-10-02 Irina Grigorescu , Lucilio Cordero-Grande , A David Edwards , Jo Hajnal , Marc Modat , Maria Deprez