Related papers: Concept frustration: Aligning human concepts and m…
Data integration is considered a classic research field and a pressing need within the information science community. Ontologies play a critical role in such a process by providing well-consolidated support to link and semantically…
How are abstract concepts and musical themes recognized on the basis of some previous experience? It is interesting to compare the different behaviors of human and of artificial intelligences with respect to this problem. Generally, a human…
Sycophancy (overly agreeable or flattering behavior) poses a fundamental challenge for human-AI collaboration, particularly in high-stakes decision-making domains such as health, law, and education. A central difficulty in studying…
As AI systems grow more capable, it becomes increasingly important that their decisions remain understandable and aligned with human expectations. A key challenge is the limited interpretability of deep models. Post-hoc methods like GradCAM…
Recent work in explanation generation for decision making agents has looked at how unexplained behavior of autonomous systems can be understood in terms of differences in the model of the system and the human's understanding of the same,…
Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background. Our observations reveal that these multi-modal models cannot distinguish…
Understanding how humans conceptualize and categorize natural objects offers critical insights into perception and cognition. With the advent of Large Language Models (LLMs), a key question arises: can these models develop human-like object…
Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains…
Large language models (LLMs) are widely described as artificial intelligence, yet their epistemic profile diverges sharply from human cognition. Here we show that the apparent alignment between human and machine outputs conceals a deeper…
Understanding how people represent categories is a core problem in cognitive science. Decades of research have yielded a variety of formal theories of categories, but validating them with naturalistic stimuli is difficult. The challenge is…
In light of the recent widespread adoption of AI systems, understanding the internal information processing of neural networks has become increasingly critical. Most recently, machine vision has seen remarkable progress by scaling neural…
Large language models (LLMs) are increasingly used as epistemic partners in everyday reasoning, yet their errors remain predominantly analyzed through predictive metrics rather than through their interpretive effects on human judgment. This…
Artificial Intelligence systems cannot yet match human abilities to apply knowledge to situations that vary from what they have been programmed for, or trained for. In visual object recognition methods of inference exploiting top-down…
Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Crucially, the CBM design inherently allows for human interventions, in which expert users are given…
Understanding convergent learning -- the degree to which independently trained neural systems -- whether multiple artificial networks or brains and models -- arrive at similar internal representations -- is crucial for both neuroscience and…
The field of artificial intelligence (AI) alignment aims to investigate whether AI technologies align with human interests and values and function in a safe and ethical manner. AI alignment is particularly relevant for large language models…
We study \emph{Human Projection} (HP): people's tendency to evaluate AI using the same frameworks they use for humans -- treating features such as task difficulty and the reasonableness of mistakes as diagnostic of overall ability. We…
Large language models often necessitate grounding on external knowledge to generate faithful and reliable answers. Yet even with the correct groundings in the reference, they can ignore them and rely on wrong groundings or their inherent…
Explainability is widely regarded as essential for trustworthy artificial intelligence systems. However, the metrics commonly used to evaluate counterfactual explanations are algorithmic evaluation metrics that are rarely validated against…
Explainable AI (XAI) underwent a recent surge in research on concept extraction, focusing on extracting human-interpretable concepts from Deep Neural Networks. An important challenge facing concept extraction approaches is the difficulty of…