We introduce the Concept Bottleneck Large Language Model (CB-LLM), a pioneering approach to creating inherently interpretable Large Language Models (LLMs). Unlike traditional black-box LLMs that rely on post-hoc interpretation methods with limited neuron function insights, CB-LLM sets a new standard with its built-in interpretability, scalability, and ability to provide clear, accurate explanations. This innovation not only advances transparency in language models but also enhances their effectiveness. Our unique Automatic Concept Correction (ACC) strategy successfully narrows the performance gap with conventional black-box LLMs, positioning CB-LLM as a model that combines the high accuracy of traditional LLMs with the added benefit of clear interpretability -- a feature markedly absent in existing LLMs.

In cancer diagnosis, classification of the different tumor types is of great importance. An accurate prediction of different tumor types provides better treatment and toxicity minimization on patients. Traditional methods of tackling this situation are primarily based on morphological characteristics of tumorous tissue [1]. These conventional methods are reported to have several diagnosis limitations. In order to analyze the problem of cancer classification using gene expression data, more systematic approaches have been developed [2]. Pioneering work in cancer classification by gene expression using DNA microarray showed the possibility to help the diagnosis by means of Machine Learning or more generally Data Mining methods [3], which are now extensively used for this task [4]. However, in this setting gene expression data analysis entails a heavy computational consumption of resources, due to the extreme sparseness compared to standard data sets in classification tasks [5]. Typically, a gene expression data set may consist of dozens of observations but with thousands or even tens of thousands of genes.

Wandering is a problematic behavior that is common among people with dementia (PwD), and is highly influenced by the elders’ background and by contextual factors specific to the situation. We have developed the Ambient Augmented Memory System (AAMS) to support the caregiver to implement interventions based on providing external memory aids to the PwD. To provide a successful intervention, it is required to use an individualized approach that considers the context of the PwD situation. To reach this end, we extended the AAMS system to include an ontological model to support the context-aware tailoring of interventions for wandering. In this paper, we illustrate the ontology flexibility to personalize the AAMS system to support direct and indirect interventions for wandering through mobile devices.