相关论文: Meaningfully Debugging Model Mistakes using Concep…

Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning based methods, they are as good as their training data, and can also capture unwanted biases.…

Interpretability research takes counterfactual theories of causality for granted. Most causal methods rely on counterfactual interventions to inputs or the activations of particular model components, followed by observations of the change…

Counterfactual explanations (CFE) are methods that explain a machine learning model by giving an alternate class prediction of a data point with some minimal changes in its features. It helps the users to identify their data attributes that…

Recent black-box counterfactual generation frameworks fail to take into account the semantic content of the proposed edits, while relying heavily on training to guide the generation process. We propose a novel, plug-and-play black-box…

While machine learning models have achieved unprecedented success in real-world applications, they might make biased/unfair decisions for specific demographic groups and hence result in discriminative outcomes. Although research efforts…

Explanations are an important tool for gaining insights into the behavior of ML models, calibrating user trust and ensuring regulatory compliance. Past few years have seen a flurry of post-hoc methods for generating model explanations, many…

Explaining deep neural networks is challenging, due to their large size and non-linearity. In this paper, we introduce a concept-based explanation method, in order to explain the prediction for an individual class, as well as contrasting…

We introduce MCCE: Monte Carlo sampling of valid and realistic Counterfactual Explanations for tabular data, a novel counterfactual explanation method that generates on-manifold, actionable and valid counterfactuals by modeling the joint…

In this paper, we show that counterfactual explanations of confidence scores help users better understand and better trust an AI model's prediction in human-subject studies. Showing confidence scores in human-agent interaction systems can…

Machine learning models perform well on several healthcare tasks and can help reduce the burden on the healthcare system. However, the lack of explainability is a major roadblock to their adoption in hospitals. \textit{How can the decision…

Although many machine learning methods, especially from the field of deep learning, have been instrumental in addressing challenges within robotic applications, we cannot take full advantage of such methods before these can provide…

Modern language models can imitate complex patterns through few-shot learning, enabling them to complete challenging tasks without fine-tuning. However, imitation can also lead models to reproduce inaccuracies or harmful content if present…

Machine Learning (ML) provides important techniques for classification and predictions. Most of these are black-box models for users and do not provide decision-makers with an explanation. For the sake of transparency or more validity of…

We consider counterfactual explanations, the problem of minimally adjusting features in a source input instance so that it is classified as a target class under a given classifier. This has become a topic of recent interest as a way to…

Foundational Vision-Language models such as CLIP have exhibited impressive generalization in downstream tasks. However, CLIP suffers from a two-level misalignment issue, i.e., task misalignment and data misalignment, when adapting to…

When language models correctly parse "The cat that the dog chased meowed," are they analyzing syntax or simply familiar with dogs chasing cats? Despite extensive benchmarking, we lack methods to distinguish structural understanding from…

Explainability, in particular, the ability for robots to explain why they have made a decision or behaved in a certain way, is a critical tool in helping users understand the robots they interact and coexist with. Behaviour trees are a…

We analyze the behavior of approximate Bayesian computation (ABC) when the model generating the simulated data differs from the actual data generating process; i.e., when the data simulator in ABC is misspecified. We demonstrate both…

We propose an architecture for training generative models of counterfactual conditionals of the form, 'can we modify event A to cause B instead of C?', motivated by applications in robot control. Using an 'adversarial training' paradigm, an…

Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who receive the intervention and those who do not. Misspecification…