English
Related papers

Related papers: Benchmarking Attribution Methods with Relative Fea…

200 papers

The objective of this paper is to assess the quality of explanation heatmaps for image classification tasks. To assess the quality of explainability methods, we approach the task through the lens of accuracy and stability. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Lassi Raatikainen , Esa Rahtu

Machine learning and deep learning models are pivotal in educational contexts, particularly in predicting student success. Despite their widespread application, a significant gap persists in comprehending the factors influencing these…

Machine Learning · Computer Science 2024-05-24 Priscylla Silva , Claudio T. Silva , Luis Gustavo Nonato

Recent state-of-the-art authorship attribution methods learn authorship representations of texts in a latent, non-interpretable space, hindering their usability in real-world applications. Our work proposes a novel approach to interpreting…

Computation and Language · Computer Science 2024-09-12 Milad Alshomary , Narutatsu Ri , Marianna Apidianaki , Ajay Patel , Smaranda Muresan , Kathleen McKeown

Unsupervised methods, such as wav2vec2 and HuBERT, have achieved state-of-the-art performance in audio tasks, leading to a shift away from research on interpretable features. However, the lack of interpretability in these methods limits…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-07 Yacouba Kaloga , Ina Kodrasi

Interpretability tools are increasingly used to analyze failures of Large Language Models (LLMs), yet prior work largely focuses on short prompts or toy settings, leaving their behavior on commonly used benchmarks underexplored. To address…

Artificial Intelligence · Computer Science 2026-04-21 Rongyuan Tan , Jue Zhang , Zhuozhao Li , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Sukrut Rao , Moritz Böhle , Bernt Schiele

We can often verify the correctness of neural network outputs using ground truth labels, but we cannot reliably determine whether the output was produced by normal or anomalous internal mechanisms. Mechanistic anomaly detection (MAD) aims…

Machine Learning · Computer Science 2026-05-26 Hugo Lyons Keenan , Christopher Leckie , Sarah Erfani

Interpretability remains a key challenge for deploying large language models (LLMs) in clinical settings such as Alzheimer's disease progression diagnosis, where early and trustworthy predictions are essential. Existing attribution methods…

Explainable AI has attracted much research attention in recent years with feature attribution algorithms, which compute "feature importance" in predictions, becoming increasingly popular. However, there is little analysis of the validity of…

Artificial Intelligence · Computer Science 2021-05-21 Orcun Yalcin , Xiuyi Fan , Siyuan Liu

Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but it…

Machine Learning · Computer Science 2026-01-29 Kurt Butler , Guanchao Feng , Petar Djuric

A recent focus of large language model (LLM) development, as exemplified by generative search engines, is to incorporate external references to generate and support its claims. However, evaluating the attribution, i.e., verifying whether…

Computation and Language · Computer Science 2023-10-10 Xiang Yue , Boshi Wang , Ziru Chen , Kai Zhang , Yu Su , Huan Sun

As the public seeks greater accountability and transparency from machine learning algorithms, the research literature on methods to explain algorithms and their outputs has rapidly expanded. Feature importance methods form a popular class…

Computers and Society · Computer Science 2021-02-01 Leif Hancox-Li , I. Elizabeth Kumar

In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, interpretability approaches should provide actionable insights without making the users wait. In this paper, we propose Accelerated…

Machine Learning · Computer Science 2021-12-24 David Dandolo , Chiara Masiero , Mattia Carletti , Davide Dalle Pezze , Gian Antonio Susto

Feature attribution methods (FAs), such as gradients and attention, are widely employed approaches to derive the importance of all input features to the model predictions. Existing work in natural language processing has mostly focused on…

Computation and Language · Computer Science 2024-02-09 Zhixue Zhao , Boxuan Shan

Explainability is needed to establish confidence in machine learning results. Some explainable methods take a post hoc approach to explain the weights of machine learning models, others highlight areas of the input contributing to…

Machine Learning · Computer Science 2024-07-15 Paul Whitten , Francis Wolff , Chris Papachristou

This paper examines and proposes several attribution modeling methods that quantify how revenue should be attributed to online advertising inputs. We adopt and further develop relative importance method, which is based on regression models…

Econometrics · Economics 2017-10-19 Kaifeng Zhao , Seyed Hanif Mahboobi , Saeed Bagheri

Feature attribution methods promise to identify which input features matter for a model output. In generative language models, however, it is often unclear what should count as a feature in the first place. In autoregressive language…

Machine Learning · Computer Science 2026-05-25 Giang Nguyen

Rigorousness and clarity are both essential for interpretations of DNNs to engender human trust. Path methods are commonly employed to generate rigorous attributions that satisfy three axioms. However, the meaning of attributions remains…

Computer Vision and Pattern Recognition · Computer Science 2024-01-22 Borui Zhang , Wenzhao Zheng , Jie Zhou , Jiwen Lu

Interpretability analysis methods for artificial intelligence models, such as LIME and SHAP, are widely used, though they primarily serve as post-model for analyzing model outputs. While it is commonly believed that the transparency and…

General Finance · Quantitative Finance 2025-02-28 Yan Zhang , Lin Chen , Yixiang Tian

In recent years, Artificial Intelligence (AI) algorithms have been proven to outperform traditional statistical methods in terms of predictivity, especially when a large amount of data was available. Nevertheless, the "black box" nature of…

Machine Learning · Statistics 2021-10-14 Nicola Picchiotti , Marco Gori