Related papers: Post hoc Explanations may be Ineffective for Detec…

Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leveraging reward models. In practice, these models often…

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Attribution scores indicate the importance of different input parts and can, thus, explain model behaviour. Currently, prompt-based models are gaining popularity, i.a., due to their easier adaptability in low-resource settings. However, the…

Many researchers have suggested that local post-hoc explanation algorithms can be used to gain insights into the behavior of complex machine learning models. However, theoretical guarantees about such algorithms only exist for simple…

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…

Many methods to explain black-box models, whether local or global, are additive. In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations…

Feature importance estimates that inform users about the degree to which given inputs influence the output of a predictive model are crucial for understanding, validating, and interpreting machine-learning models. However, providing fast…

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…

Feature attribution methods are widely used for explaining image-based predictions, as they provide feature-level insights that can be intuitively visualized. However, such explanations often vary in their robustness and may fail to…

Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a…

Learning causal relationships between pairs of complex traits from observational studies is of great interest across various scientific domains. However, most existing methods assume the absence of unmeasured confounding and restrict causal…

Counterfactual post-hoc interpretability approaches have been proven to be useful tools to generate explanations for the predictions of a trained blackbox classifier. However, the assumptions they make about the data and the classifier make…

Weak signal identification and inference are very important in the area of penalized model selection, yet they are under-developed and not well-studied. Existing inference procedures for penalized estimators are mainly focused on strong…

Feature attribution methods highlight the important input tokens as explanations to model predictions, which have been widely applied to deep neural networks towards trustworthy AI. However, recent works show that explanations provided by…

Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. This goal is usually approached with attribution method, which assesses the influence of features…

Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging…

Many data mining and statistical machine learning algorithms have been developed to select a subset of covariates to associate with a response variable. Spurious discoveries can easily arise in high-dimensional data analysis due to enormous…

Concept-based approaches, which aim to identify human-understandable concepts within a model's internal representations, are a promising method for interpreting embeddings from deep neural network models, such as CLIP. While these…

An important limitation to the development of AI-based solutions for In Vitro Fertilization (IVF) is the black-box nature of most state-of-the-art models, due to the complexity of deep learning architectures, which raises potential bias and…

This paper provides partial identification of various binary choice models with misreported dependent variables. We propose two distinct approaches by exploiting different instrumental variables respectively. In the first approach, the…