Related papers: Dissonance Between Human and Machine Understanding

Deep neural networks have demonstrated remarkable performance in many data-driven and prediction-oriented applications, and sometimes even perform better than humans. However, their most significant drawback is the lack of interpretability,…

Modern neural networks (NNs) often achieve high predictive accuracy but are poorly calibrated, producing overconfident predictions even when wrong. This miscalibration poses serious challenges in applications where reliable uncertainty…

Explaining black-box Artificial Intelligence (AI) models is a cornerstone for trustworthy AI and a prerequisite for its use in safety critical applications such that AI models can reliably assist humans in critical decisions. However,…

Rapid categorization paradigms have a long history in experimental psychology: Characterized by short presentation times and speedy behavioral responses, these tasks highlight the efficiency with which our visual system processes natural…

Recent advances in AI -- including generative approaches -- have resulted in technology that can support humans in scientific discovery and forming decisions, but may also disrupt democracies and target individuals. The responsible use of…

Machine learning (ML) and artificial intelligence (AI) tools increasingly permeate every possible social, political, and economic sphere; sorting, taxonomizing and predicting complex human behaviour and social phenomena. However, from…

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Human-in-the-loop aims to train an accurate prediction model with minimum cost by integrating human knowledge and experience. Humans can provide training data for machine learning applications and directly accomplish tasks that are hard for…

Large language models are increasingly used in decision-making tasks that require them to process information from a variety of sources, including both human experts and other algorithmic agents. How do LLMs weigh the information provided…

Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this…

Large Language Models (LLMs) have demonstrated their capabilities across various tasks, from language translation to complex reasoning. Understanding and predicting human behavior and biases are crucial for artificial intelligence (AI)…

Machine reading comprehension (MRC) aims to teach machines to read and comprehend human languages, which is a long-standing goal of natural language processing (NLP). With the burst of deep neural networks and the evolution of…

Predicting the collaboration likelihood and measuring cognitive trust to AI systems is more important than ever. To do that, previous research mostly focus solely on the model features (e.g., accuracy, confidence) and ignore the human…

Deep neural network (DNN) models have achieved phenomenal success for applications in many domains, ranging from academic research in science and engineering to industry and business. The modeling power of DNN is believed to have come from…

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…

Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven powerful for a wide range of downstream tasks, it fundamentally differs from the way humans…

Humans should be able work more effectively with artificial intelligence-based systems when they can predict likely failures and form useful mental models of how the systems work. We conducted a study of human's mental models of artificial…

We introduce a benchmark to directly evaluate the alignment between human observers and vision models on a 3D shape inference task. We leverage an experimental design from the cognitive sciences which requires zero-shot visual inferences…

Machine learning (ML) models that achieve high average accuracy can still underperform on semantically coherent subsets ("slices") of data. This behavior can have significant societal consequences for the safety or bias of the model in…

Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an…