Publications associées à Right to explanation

The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations

Vinitra Swamy, Tanja Christina Käser Jacober, Jibril Albachir Frej

Explainable Artificial Intelligence (XAI) plays a crucial role in enabling human understanding and trust in deep learning systems, often defined as determining which features are most important to a model's prediction. As models get larger, more ubiquitous ...

2023

Towards Visual Saliency Explanations of Face Verification

Touradj Ebrahimi, Yuhang Lu, Zewei Xu

In the past years, deep convolutional neural networks have been pushing the frontier of face recognition (FR) techniques in both verification and identification scenarios. Despite the high accuracy, they are often criticized for lacking explainability. The ...

2024

Multi-Dimensional Explanation of Target Variables from Documents

Boi Faltings, Claudiu-Cristian Musat, Diego Matteo Antognini

Automated predictions require explanations to be interpretable by humans. Past work used attention and rationale mechanisms to find words that predict the target variable of a document. Often though, they result in a tradeoff between noisy explanations or ...

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE2021

Execution Synthesis: A Technique for Automated Software Debugging

George Candea, Cristian Zamfir

Debugging real systems is hard, requires deep knowledge of the code, and is time-consuming. Bug reports rarely provide sufficient information, thus forcing developers to turn into detectives searching for an explanation of how the program could have arrive ...

2010