Aligned Large Language Models (LLMs) showcase remarkable versatility, capable of
handling diverse real-world tasks. Meanwhile, aligned LLMs are also expected to exhibit …

The multimodal deep neural networks, represented by CLIP, have generated rich
downstream applications owing to their excellent performance, thus making understanding …

Artificial Intelligence (AI) methods are powerful tools for various domains, including critical
fields such as avionics, where certification is required to achieve and maintain an …

Concept Bottleneck Models (CBM) map images to human-interpretable concepts before
making class predictions. Recent approaches automate CBM construction by prompting …

Models based on human-understandable concepts have received extensive attention to
improve model interpretability for trustworthy artificial intelligence in the field of medical …

As AI models grow larger, the demand for accountability and interpretability has become
increasingly critical for understanding their decision-making processes. Concept Bottleneck …

Concept bottleneck models (CBMs) are inherently interpretable models that make
predictions based on human-understandable visual cues, referred to as concepts. As …