English
Related papers

Related papers: How to Probe: Simple Yet Effective Techniques for …

200 papers

Post-hoc explainability methods such as Grad-CAM are popular because they do not influence the performance of a trained model. However, they mainly reveal "where" a model looks at for a given input, fail to explain "what" the model looks…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Andong Tan , Fengtao Zhou , Hao Chen

Machine learning models are widely applied in various fields. Stakeholders often use post-hoc feature importance methods to better understand the input features' contribution to the models' predictions. The interpretation of the importance…

Machine Learning · Statistics 2024-04-19 Bitya Neuhof , Yuval Benjamini

As complex machine learning models continue to find applications in high-stakes decision-making scenarios, it is crucial that we can explain and understand their predictions. Post-hoc explanation methods provide useful insights by…

Machine Learning · Statistics 2024-10-16 Beepul Bharti , Paul Yi , Jeremias Sulam

Pre-training has exhibited notable benefits to downstream tasks by boosting accuracy and speeding up convergence, but the exact reasons for these benefits still remain unclear. To this end, we propose to quantitatively and explicitly…

Machine Learning · Computer Science 2024-10-14 Xin Jiang , Xu Cheng , Zechao Li

Artificial intelligence models are increasingly scaled to improve predictive accuracy, yet it remains unclear whether scale improves the quality of post-hoc explanations. We investigate this relationship by evaluating 11 computer vision…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Mateusz Cedro , Marcin Chlebus

As neural networks increasingly make critical decisions in high-stakes settings, monitoring and explaining their behavior in an understandable and trustworthy manner is a necessity. One commonly used type of explainer is post hoc feature…

Machine Learning · Computer Science 2023-03-24 Avi Schwarzschild , Max Cembalest , Karthik Rao , Keegan Hines , John Dickerson

The majority of existing post-hoc explanation approaches for machine learning models produce independent, per-variable feature attribution scores, ignoring a critical inherent characteristics of homogeneously structured data, such as visual…

Machine Learning · Computer Science 2023-02-14 Vadim Borisov , Gjergji Kasneci

Explainable AI (XAI) methods generally fall into two categories. Post-hoc approaches generate explanations for pre-trained models and are compatible with various neural network architectures. These methods often use feature importance…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Piotr Borycki , Magdalena Trędowicz , Szymon Janusz , Jacek Tabor , Przemysław Spurek , Arkadiusz Lewicki , Łukasz Struski

The goal of data attribution is to trace the model's predictions through the learning algorithm and back to its training data. thereby identifying the most influential training samples and understanding how the model's behavior leads to…

Machine Learning · Computer Science 2025-08-12 Hongbo Zhu , Angelo Cangelosi

Recent deep-learning models have achieved impressive predictive performance by learning complex functions of many variables, often at the cost of interpretability. This chapter covers recent work aiming to interpret models by attributing…

Machine Learning · Statistics 2021-08-20 Chandan Singh , Wooseok Ha , Bin Yu

Post-hoc interpretability methods typically attribute a model's behavior to its components, data, or training trajectory in isolation. This leads to explanations that lack a unified view and may miss key interactions. While combining…

Machine Learning · Computer Science 2025-10-02 Florian Eichin , Yupei Du , Philipp Mondorf , Maria Matveev , Barbara Plank , Michael A. Hedderich

Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a…

Machine Learning · Computer Science 2019-12-09 Ramaravind Kommiya Mothilal , Amit Sharma , Chenhao Tan

Neural networks are increasingly finding their way into the realm of graphs and modeling relationships between features. Concurrently graph neural network explanation approaches are being invented to uncover relationships between the nodes…

Machine Learning · Computer Science 2024-01-02 Razieh Rezaei , Alireza Dizaji , Ashkan Khakzar , Anees Kazi , Nassir Navab , Daniel Rueckert

Recent work in Natural Language Processing has focused on developing approaches that extract faithful explanations, either via identifying the most important tokens in the input (i.e. post-hoc explanations) or by designing inherently…

Computation and Language · Computer Science 2022-03-02 George Chrysostomou , Nikolaos Aletras

This position paper defends post-hoc explainability methods as legitimate tools for scientific knowledge production in machine learning. Addressing criticism of these methods' reliability and epistemic status, we develop a philosophical…

Machine Learning · Computer Science 2025-10-31 Nick Oh

As post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to ensure that the quality of the resulting explanations is consistently high across various population…

Machine Learning · Computer Science 2022-07-05 Jessica Dai , Sohini Upadhyay , Ulrich Aivodji , Stephen H. Bach , Himabindu Lakkaraju

EXplainable AI has received significant attention in recent years. Machine learning models often operate as black boxes, lacking explainability and transparency while supporting decision-making processes. Local post-hoc explainability…

Artificial Intelligence · Computer Science 2024-05-24 Gianvincenzo Alfano , Sergio Greco , Domenico Mandaglio , Francesco Parisi , Reza Shahbazian , Irina Trubitsyna

Post hoc explanations have emerged as a way to improve user trust in machine learning models by providing insight into model decision-making. However, explanations tend to be evaluated based on their alignment with prior knowledge while the…

Human-Computer Interaction · Computer Science 2023-12-13 Tessa Han , Yasha Ektefaie , Maha Farhat , Marinka Zitnik , Himabindu Lakkaraju

Saliency post-hoc explainability methods are important tools for understanding increasingly complex NLP models. While these methods can reflect the model's reasoning, they may not align with human intuition, making the explanations not…

Computation and Language · Computer Science 2024-08-20 Lucas E. Resck , Marcos M. Raimundo , Jorge Poco

Predictive models are omnipresent in automated and assisted decision making scenarios. But for the most part they are used as black boxes which output a prediction without understanding partially or even completely how different features…

Information Retrieval · Computer Science 2018-07-02 Jaspreet Singh , Avishek Anand