Related papers: Enhancing Actionable Formal Concept Identification…
The concept of identifiability describes the possibility of inferring the parameters of a dynamic model by observing its output. It is common and useful to distinguish between structural and practical identifiability. The former property is…
In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate…
Image aesthetic quality assessment (AQA) aims to assign numerical aesthetic ratings to images whilst image aesthetic captioning (IAC) aims to generate textual descriptions of the aesthetic aspects of images. In this paper, we study image…
Given a database and a target attribute of interest, how can we tell whether there exists a functional, or approximately functional dependence of the target on any set of other attributes in the data? How can we reliably, without bias to…
Concept learning exploits background knowledge in the form of description logic axioms to learn explainable classification models from knowledge bases. Despite recent breakthroughs in neuro-symbolic concept learning, most approaches still…
Evaluating the quality and variability of text generated by Large Language Models (LLMs) poses a significant, yet unresolved research challenge. Traditional evaluation methods, such as ROUGE and BERTScore, which measure token similarity,…
The ability to efficiently search for images is essential for improving the user experiences across various products. Incorporating user feedback, via multi-modal inputs, to navigate visual search can help tailor retrieved results to…
Counterfactual examples are widely used in natural language processing (NLP) as valuable data to improve models, and in explainable artificial intelligence (XAI) to understand model behavior. The automated generation of counterfactual…
We introduce a data-centric hypothesis-testing framework to quantify the influence of sequentially correlated literary properties--such as thematic continuity--on textual classification tasks. Our method models label sequences as stochastic…
Formal Concept Analysis (FCA) offers several tools for qualitative data analysis. One possibility is to group objects that share common attributes together and get a concept lattice that describes the data. Quite often the size of this…
In a university, research assessments are organized at different policy levels (faculties, research council) in different contexts (funding, council membership, personnel evaluations). Each evaluation requires its own focus and methodology.…
Many automatic attribute discovery methods have been developed to extract a set of visual attributes from images for various tasks. However, despite good performance in some image classification tasks, it is difficult to evaluate whether…
Explainable object recognition using vision-language models such as CLIP involves predicting accurate category labels supported by rationales that justify the decision-making process. Existing methods typically rely on prompt-based…
Despite the popularity of Formal Concept Analysis (FCA) as a mathematical framework for data analysis, some of its extensions are still considered arcane. Polyadic Concept Analysis (PCA) is one of the most promising yet understudied of…
A feature concept, the essence of the data-federative innovation process, is presented as a model of the concept to be acquired from data. A feature concept may be a simple feature, such as a single variable, but is more likely to be a…
Traditional information retrieval systems rely on keywords to index documents and queries. In such systems, documents are retrieved based on the number of shared keywords with the query. This lexical-focused retrieval leads to inaccurate…
In the realm of the model selection context, Akaike's and Schwarz's information criteria, AIC and BIC, have been applied successfully for decades for model order identification. The Efficient Determination Criterion (EDC) is a…
Interest in understanding and factorizing learned embedding spaces through conceptual explanations is steadily growing. When no human concept labels are available, concept discovery methods search trained embedding spaces for interpretable…
While the existence of many security elements can be measured (e.g., vulnerabilities, security controls, or privacy controls), it is challenging to measure their relative security impact. In the physical world we can often measure the…
The rapid development of large language models has led to the widespread adoption of Retrieval-Augmented Generation (RAG), which integrates external knowledge to alleviate knowledge bottlenecks and mitigate hallucinations. However, the…