Related papers: Debugging Tests for Model Explanations

Neural networks for NLP are becoming increasingly complex and widespread, and there is a growing concern if these models are responsible to use. Explaining models helps to address the safety and ethical concerns and is essential for…

Acquiring and training on large-scale labeled data can be impractical due to cost constraints. Additionally, the use of small training datasets can result in considerable variability in model outcomes, overfitting, and learning of spurious…

From simulating galaxy formation to viral transmission in a pandemic, scientific models play a pivotal role in developing scientific theories and supporting government policy decisions that affect us all. Given these critical applications,…

The use of complex machine learning models can make systems opaque to users. Machine learning research proposes the use of post-hoc explanations. However, it is unclear if they give users insights into otherwise uninterpretable models. One…

Much machine learning research progress is based on developing models and evaluating them on a benchmark dataset (e.g., ImageNet for images). However, applying such benchmark-successful methods to real-world data often does not work as…

Despite being highly performant, deep neural networks might base their decisions on features that spuriously correlate with the provided labels, thus hurting generalization. To mitigate this, 'model guidance' has recently gained popularity,…

Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal of providing such explanations, and how can we demonstrate…

Responsible use of machine learning requires models to be audited for undesirable properties. While a body of work has proposed using explanations for auditing, how to do so and why has remained relatively ill-understood. This work…

Post-hoc explanation methods are used with the intent of providing insights about neural networks and are sometimes said to help engender trust in their outputs. However, popular explanations methods have been found to be fragile to minor…

The interpretability of machine learning models has gained increasing attention, particularly in scientific domains where high precision and accountability are crucial. This research focuses on distinguishing between two critical data…

Fault detection and diagnosis of electrical motors are of utmost importance in ensuring the safe and reliable operation of several industrial systems. Detection and diagnosis of faults at the incipient stage allows corrective actions to be…

Interpretability, trustworthiness, and usability are key considerations in high-stake security applications, especially when utilizing deep learning models. While these models are known for their high accuracy, they behave as black boxes in…

Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released language models. As a countermeasure, backdoor detection methods…

Deep learning models have achieved remarkable success in different areas of machine learning over the past decade; however, the size and complexity of these models make them difficult to understand. In an effort to make them more…

Due to language models' propensity to generate toxic or hateful responses, several techniques were developed to align model generations with users' preferences. Despite the effectiveness of such methods in improving the safety of model…

Recent studies highlight various machine learning (ML)-based techniques for code clone detection, which can be integrated into developer tools such as static code analysis. With the advancements brought by ML in code understanding, ML-based…

Recently, pretrained language models have shown state-of-the-art performance on the vulnerability detection task. These models are pretrained on a large corpus of source code, then fine-tuned on a smaller supervised vulnerability dataset.…

This study proposes an innovative explainable predictive quality analytics solution to facilitate data-driven decision-making for process planning in manufacturing by combining process mining, machine learning, and explainable artificial…

Training set bugs are flaws in the data that adversely affect machine learning. The training set is usually too large for man- ual inspection, but one may have the resources to verify a few trusted items. The set of trusted items may not by…

Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive {\em uncertainty}. Quantifying…