English
Related papers

Related papers: Explanation Multiplicity in SHAP: Characterization…

200 papers

The growing complexity of machine learning and deep learning models has led to an increased reliance on opaque "black box" systems, making it difficult to understand the rationale behind predictions. This lack of transparency is…

Machine Learning · Computer Science 2025-02-06 Pratinav Seth , Yashwardhan Rathore , Neeraj Kumar Singh , Chintan Chitroda , Vinay Kumar Sankarapu

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

SHAP explanations aim at identifying which features contribute the most to the difference in model prediction at a specific input versus a background distribution. Recent studies have shown that they can be manipulated by malicious…

Machine Learning · Computer Science 2023-03-06 Gabriel Laberge , Ulrich Aïvodji , Satoshi Hara , Mario Marchand. , Foutse Khomh

Machine learning models are often used to inform real world risk assessment tasks: predicting consumer default risk, predicting whether a person suffers from a serious illness, or predicting a person's risk to appear in court. Given…

Machine Learning · Computer Science 2023-06-27 Jamelle Watson-Daniels , David C. Parkes , Berk Ustun

The ubiquitous use of Shapley values in eXplainable AI (XAI) has been triggered by the tool SHAP, and as a result are commonly referred to as SHAP scores. Recent work devised examples of machine learning (ML) classifiers for which the…

Machine Learning · Computer Science 2024-12-20 Olivier Letoffe , Xuanxiang Huang , Joao Marques-Silva

Post-hoc interpretability methods play a critical role in explainable artificial intelligence (XAI), as they pinpoint portions of data that a trained deep learning model deemed important to make a decision. However, different post-hoc…

Machine Learning · Computer Science 2024-07-30 Jiawen Wei , Hugues Turbé , Gianmarco Mengaldo

Understanding the decisions made and actions taken by increasingly complex AI system remains a key challenge. This has led to an expanding field of research in explainable artificial intelligence (XAI), highlighting the potential of…

Large Language Models (LLMs) and Large Reasoning Models (LRMs) are increasingly used for critical tasks, yet they provide no guarantees about the correctness of their solutions. Users must decide whether to trust the model's answer, aided…

Human-Computer Interaction · Computer Science 2026-05-19 Vardhan Palod , Upasana Biswas , Subbarao Kambhampati

Deep Learning methods are renowned for their performances, yet their lack of interpretability prevents them from high-stakes contexts. Recent model agnostic methods address this problem by providing post-hoc interpretability methods by…

Machine Learning · Computer Science 2021-11-30 Marco Repetto

Explainable AI (XAI) aims to support appropriate human-AI reliance by increasing the interpretability of complex model decisions. Despite the proliferation of proposed methods, there is mixed evidence surrounding the effects of different…

Human-Computer Interaction · Computer Science 2024-10-29 Emma Casolin , Flora D. Salim , Ben Newell

Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little consensus on practical deployment. While theoretical differences are well-documented,…

Machine Learning · Computer Science 2026-04-27 Inês Oliveira e Silva , Sérgio Jesus , Iker Perez , Rita P. Ribeiro , Carlos Soares , Hugo Ferreira , Pedro Bizarro

A number of techniques have been proposed to explain a machine learning model's prediction by attributing it to the corresponding input features. Popular among these are techniques that apply the Shapley value method from cooperative game…

Machine Learning · Computer Science 2020-06-29 Luke Merrick , Ankur Taly

Post-hoc recalibration methods are widely used to ensure that classifiers provide faithful probability estimates. We argue that parametric recalibration functions based on logistic regression can be motivated from a simple theoretical…

Machine Learning · Computer Science 2026-03-11 Eugène Berta , David Holzmüller , Michael I. Jordan , Francis Bach

Explainability is a critical factor in enhancing the trustworthiness and acceptance of artificial intelligence (AI) in healthcare, where decisions directly impact patient outcomes. Despite advancements in AI interpretability, clear…

Artificial Intelligence · Computer Science 2025-05-15 Michail Mamalakis , Héloïse de Vareilles , Graham Murray , Pietro Lio , John Suckling

Artificial Intelligence (AI) systems are increasingly used in high-stakes domains of our life, increasing the need to explain these decisions and to make sure that they are aligned with how we want the decision to be made. The field of…

Artificial Intelligence · Computer Science 2023-06-28 Sofie Goethals , David Martens , Theodoros Evgeniou

The recent enthusiasm for artificial intelligence (AI) is due principally to advances in deep learning. Deep learning methods are remarkably accurate, but also opaque, which limits their potential use in safety-critical applications. To…

A growing effort in NLP aims to build datasets of human explanations. However, the term explanation encompasses a broad range of notions, each with different properties and ramifications. Our goal is to provide an overview of diverse types…

Computation and Language · Computer Science 2022-05-17 Chenhao Tan

The most common methods in explainable artificial intelligence are post-hoc techniques which identify the most relevant features used by pretrained opaque models. Some of the most advanced post hoc methods can generate explanations that…

Artificial Intelligence · Computer Science 2026-03-11 Stefano Fioravanti , Francesco Giannini , Paolo Frazzetto , Fabio Zanasi , Pietro Barbiero

SHAP is a popular method for measuring variable importance in machine learning models. In this paper, we study the algorithm used to estimate SHAP scores and outline its connection to the functional ANOVA decomposition. We use this…

Methodology · Statistics 2022-11-14 Andrew Herren , P. Richard Hahn

Post-hoc explanation methods are an important tool for increasing model transparency for users. Unfortunately, the currently used methods for attributing token importance often yield diverging patterns. In this work, we study potential…

Computation and Language · Computer Science 2024-03-29 Jonathan Kamp , Lisa Beinborn , Antske Fokkens
‹ Prev 1 4 5 6 7 8 10 Next ›