Related papers: Do AI Models Perform Human-like Abstract Reasoning…

While attention has been an increasingly popular component in deep neural networks to both interpret and boost the performance of models, little work has examined how attention progresses to accomplish a task and whether it is reasonable.…

While attention has been an increasingly popular component in deep neural networks to both interpret and boost performance of models, little work has examined how attention progresses to accomplish a task and whether it is reasonable. In…

One of the challenges facing artificial intelligence research today is designing systems capable of utilizing systematic reasoning to generalize to new tasks. The Abstraction and Reasoning Corpus (ARC) measures such a capability through a…

The Abstraction and Reasoning Corpus (ARC-AGI) presents a formidable challenge for AI systems. Despite the typically low performance on ARC, the deep learning paradigm remains the most effective known strategy for generating skillful…

A foundational principle in cognitive science holds that intelligent agents do not learn by storing experiences as isolated instances, but by forming abstract schemas that capture relational structure shared across situations. Even though…

The pursuit of artificial general intelligence necessitates robust methods for evaluating the cognitive capabilities of models beyond narrow task performance. Here, we introduce a psychometric framework to assess the cognitive profiles of…

Artificial intelligence (AI) is becoming increasingly complex, making it difficult for users to understand how the AI has derived its prediction. Using explainable AI (XAI)-methods, researchers aim to explain AI decisions to users. So far,…

One of today's most significant societal challenges is building AI systems whose behaviour, or the behaviour it enables within communities of interacting agents (human and artificial), aligns with human values. To address this challenge, we…

Abstract visual reasoning is a characteristically human ability, allowing the identification of relational patterns that are abstracted away from object features, and the systematic generalization of those patterns to unseen problems.…

The study of causal abstractions bridges two integral components of human intelligence: the ability to determine cause and effect, and the ability to interpret complex patterns into abstract concepts. Formally, causal abstraction frameworks…

Core knowledge about physical objects -- e.g., their permanency, spatial transformations, and interactions -- is one of the most fundamental building blocks of biological intelligence across humans and non-human animals. While AI techniques…

Concept-based explainable artificial intelligence (C-XAI) can let people see which representations an AI model has learned. This is particularly important when high-level semantic information (e.g., actions and relations) is used to make…

A core component of human intelligence is the ability to identify abstract patterns inherent in complex, high-dimensional perceptual data, as exemplified by visual reasoning tasks such as Raven's Progressive Matrices (RPM). Motivated by the…

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Understanding how humans and AI systems interpret ambiguous visual stimuli offers critical insight into the nature of perception, reasoning, and decision-making. This paper examines image labeling performance across human participants and…

We identify a fundamental incompatibility between the goals of accuracy, trust, and human-level reasoning in artificial intelligence (AI) systems, for strict mathematical definitions of these notions. We define accuracy of a system as the…

Do AI systems truly understand human concepts or merely mimic surface patterns? We investigate this through chess, where human creativity meets precise strategic concepts. Analyzing a 270M-parameter transformer that achieves…

IQ testing has served as a foundational methodology for evaluating human cognitive capabilities, deliberately decoupling assessment from linguistic background, language proficiency, or domain-specific knowledge to isolate core competencies…

With the emergence of advanced reasoning models like OpenAI o3 and DeepSeek-R1, large language models (LLMs) have demonstrated remarkable reasoning capabilities. However, their ability to perform rigorous logical reasoning remains an open…

Research has repeatedly demonstrated that intermediate hidden states extracted from large language models and speech audio models predict measured brain response to natural language stimuli. Yet, very little is known about the…