Related papers: Towards Fine-Grained and Verifiable Concept Bottle…

Concept-based learning enhances prediction accuracy and interpretability by leveraging high-level, human-understandable concepts. However, existing CBL frameworks do not address survival analysis tasks, which involve predicting event times…

We propose an automated genomic interpretation module that transforms raw DNA sequences into actionable, interpretable decisions suitable for integration into medical automation and robotic systems. Our framework combines Chaos Game…

Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts are more effective than those relying primarily on low-level…

Concept-based models aim to explain model decisions with human-understandable concepts. However, most existing approaches treat concepts as numerical attributes, without providing complementary visual explanations that could localize the…

Automated essay scoring (AES) has advanced significantly with neural language models, yet most systems remain opaque, offering little visibility into how grades are produced. In educational settings, instructors must be able to understand,…

Concept bottleneck model (CBM) is a ubiquitous method that can interpret neural networks using concepts. In CBM, concepts are inserted between the output layer and the last intermediate layer as observable values. This helps in…

Concept Bottleneck Models (CBMs) in medical imaging aim to improve model interpretability by predicting intermediate clinical concepts before final diagnoses. However, most existing CBMs treat concepts as discriminative predictors of…

Artificial Intelligence (AI) systems have shown good success at classifying. However, the lack of explainability is a true and significant challenge, especially in high-stakes domains, such as health and finance, where understanding is…

Continuous prompts have become widely adopted for augmenting performance across a wide range of natural language tasks. However, the underlying mechanism of this enhancement remains obscure. Previous studies rely on individual words for…

Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model…

We propose a new approach to promote safety in classification tasks with established concepts. Our approach -- called a conceptual safeguard -- acts as a verification layer for models that predict a target outcome by first predicting the…

While RFML is expected to be a key enabler of future wireless standards, a significant challenge to the widespread adoption of RFML techniques is the lack of explainability in deep learning models. This work investigates the use of CB…

Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the feature representations learned by the models. This work…

Artificial intelligence (AI) is transforming scientific research, with explainable AI methods like concept-based models (CMs) showing promise for new discoveries. However, in molecular science, CMs are less common than black-box models like…

We introduce Graph Concept Bottleneck (GCB) as a new paradigm for self-explainable text-attributed graph learning. GCB maps graphs into a subspace, concept bottleneck, where each concept is a meaningful phrase, and predictions are made…

Concept bottleneck models have been successfully used for explainable machine learning by encoding information within the model with a set of human-defined concepts. In the context of human-assisted or autonomous driving, explainability…

Machine learning models that incorporate concept learning as an intermediate step in their decision making process can match the performance of black-box predictive models while retaining the ability to explain outcomes in human…

We seek to learn models that we can interact with using high-level concepts: if the model did not think there was a bone spur in the x-ray, would it still predict severe arthritis? State-of-the-art models today do not typically support the…

We introduce the Consensus-Bottleneck Asset Pricing Model (CB-APM), which embeds aggregate analyst consensus as a structural bottleneck, treating professional beliefs as a sufficient statistic for the market's high-dimensional information…

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs…