相关论文: Measurable Counterfactual Local Explanations for A…

Modern applications require methods that are computationally feasible on large datasets but also preserve statistical efficiency. Frequently, these two concerns are seen as contradictory: approximation methods that enable computation are…

Reward models (RMs) are a crucial component in the alignment of large language models' (LLMs) outputs with human values. RMs approximate human preferences over possible LLM responses to the same prompt by predicting and comparing reward…

Multimodal classifiers function as opaque black box models. While several techniques exist to interpret their predictions, very few of them are as intuitive and accessible as natural language explanations (NLEs). To build trust, such…

As machine learning models evolve, maintaining transparency demands more human-centric explainable AI techniques. Counterfactual explanations, with roots in human reasoning, identify the minimal input changes needed to obtain a given output…

Learning representations unaffected by superficial characteristics is important to ensure that shifts in these characteristics at test time do not compromise downstream prediction performance. For instance, in healthcare applications, we…

Counterfactual explanations (CEs) enhance the interpretability of machine learning models by describing what changes to an input are necessary to change its prediction to a desired class. These explanations are commonly used to guide users'…

In many settings, it is important that a model be capable of providing reasons for its predictions (i.e., the model must be interpretable). However, the model's reasoning may not conform with well-established knowledge. In such cases, while…

Understanding why a model makes certain predictions is crucial when adapting it for real world decision making. LIME is a popular model-agnostic feature attribution method for the tasks of classification and regression. However, the task of…

Counterfactual explanations are widely used to interpret machine learning predictions by identifying minimal changes to input features that would alter a model's decision. However, most existing counterfactual methods have not been tested…

Counterfactual explanations (CFEs) guide users on how to adjust inputs to machine learning models to achieve desired outputs. While existing research primarily addresses static scenarios, real-world applications often involve data or model…

The recent years have witnessed the rise of accurate but obscure decision systems which hide the logic of their internal decision processes to the users. The lack of explanations for the decisions of black box systems is a key ethical…

Counterfactual explanation methods interpret the outputs of a machine learning model in the form of "what-if scenarios" without compromising the fidelity-interpretability trade-off. They explain how to obtain a desired prediction from the…

Automated fact checking systems have been proposed that quickly provide veracity prediction at scale to mitigate the negative influence of fake news on people and on public opinion. However, most studies focus on veracity classifiers of…

Counterfactual Explanations (CFEs) have grown in popularity as a means of offering actionable guidance by identifying the minimum changes in feature values required to flip an ML model's prediction to something more desirable.…

Recently, there has been increased interest in fair generative models. In this work, we conduct, for the first time, an in-depth study on fairness measurement, a critical component in gauging progress on fair generative models. We make…

To collaborate effectively with humans, language models must be able to explain their decisions in natural language. We study a specific type of self-explanation: self-generated counterfactual explanations (SCEs), where a model explains its…

This paper addresses the challenge of generating Counterfactual Explanations (CEs), involving the identification and modification of the fewest necessary features to alter a classifier's prediction for a given image. Our proposed method,…

We discover a theoretical connection between explanation estimation and distribution compression that significantly improves the approximation of feature attributions, importance, and effects. While the exact computation of various machine…

We evaluate two popular local explainability techniques, LIME and SHAP, on a movie recommendation task. We discover that the two methods behave very differently depending on the sparsity of the data set. LIME does better than SHAP in dense…

Transparency is a fundamental requirement for decision making systems when these should be deployed in the real world. It is usually achieved by providing explanations of the system's behavior. A prominent and intuitive type of explanations…