Large language models (LLMs) have achieved remarkable performance in generating human-like text and solving reasoning tasks of moderate complexity, such as question-answering and mathematical problem-solving. However, their capabilities in tasks requiring deeper cognitive skills, such as common-sense understanding and abstract reasoning, remain under-explored. In this paper, we systematically evaluate abstract common-sense reasoning in LLMs using the ConceptNet knowledge graph. We propose two prompting approaches: instruct prompting, where models predict plausible semantic relationships based on provided definitions, and few-shot prompting, where models identify relations using examples as guidance. Our experiments with the gpt-4o-mini model show that in instruct prompting, consistent performance is obtained when ranking multiple relations but with substantial decline when the model is restricted to predicting only one relation. In few-shot prompting, the model's accuracy improves significantly when selecting from five relations rather than the full set, although with notable bias toward certain relations. These results suggest significant gaps still, even in commercially used LLMs' abstract common-sense reasoning abilities, compared to human-level understanding. However, the findings also highlight the promise of careful prompt engineering, based on selective retrieval, for obtaining better performance.

Large Language Models (LLMs) have demonstrated remarkable success in tasks like the Winograd Schema Challenge (WSC), showcasing advanced textual common-sense reasoning. However, applying this reasoning to multimodal domains, where understanding text and images together is essential, remains a substantial challenge. To address this, we introduce WinoVis, a novel dataset specifically designed to probe text-to-image models on pronoun disambiguation within multimodal contexts. Utilizing GPT-4 for prompt generation and Diffusion Attentive Attribution Maps (DAAM) for heatmap analysis, we propose a novel evaluation framework that isolates the models' ability in pronoun disambiguation from other visual processing challenges. Evaluation of successive model versions reveals that, despite incremental advancements, Stable Diffusion 2.0 achieves a precision of 56.7% on WinoVis, only marginally surpassing random guessing. Further error analysis identifies important areas for future research aimed at advancing text-to-image models in their ability to interpret and interact with the complex visual world.

A new "common-sense" approach to computer vision enables artificial intelligence that interprets scenes more accurately than other systems do. Computer vision systems sometimes make inferences about a scene that fly in the face of common sense. For example, if a robot were processing a scene of a dinner table, it might completely ignore a bowl that is visible to any human observer, estimate that a plate is floating above the table, or misperceive a fork to be penetrating a bowl rather than leaning against it. Move that computer vision system to a self-driving car and the stakes become much higher -- for example, such systems have failed to detect emergency vehicles and pedestrians crossing the street. To overcome these errors, MIT researchers have developed a framework that helps machines see the world more like humans do. Their new artificial intelligence system for analyzing scenes learns to perceive real-world objects from just a few images, and perceives scenes in terms of these learned objects.

Computer vision systems sometimes make inferences about a scene that fly in the face of common sense. For example, if a robot were processing a scene of a dinner table, it might completely ignore a bowl that is visible to any human observer, estimate that a plate is floating above the table, or misperceive a fork to be penetrating a bowl rather than leaning against it. Move that computer vision system to a self-driving car and the stakes become much higher --for example, such systems have failed to detect emergency vehicles and pedestrians crossing the street. To overcome these errors, MIT researchers have developed a framework that helps machines see the world more like humans do. Their new artificial intelligence system for analyzing scenes learns to perceive real-world objects from just a few images, and perceives scenes in terms of these learned objects. The researchers built the framework using probabilistic programming, an AI approach that enables the system to cross-check detected objects against input data, to see if the images recorded from a camera are a likely match to any candidate scene.

Computer vision systems sometimes make inferences about a scene that fly in the face of common sense. For example, if a robot were processing a scene of a dinner table, it might completely ignore a bowl that is visible to any human observer, estimate that a plate is floating above the table, or misperceive a fork to be penetrating a bowl rather than leaning against it. Move that computer vision system to a self-driving car and the stakes become much higher -- for example, such systems have failed to detect emergency vehicles and pedestrians crossing the street. To overcome these errors, MIT researchers have developed a framework that helps machines see the world more like humans do. Their new artificial intelligence system for analyzing scenes learns to perceive real-world objects from just a few images, and perceives scenes in terms of these learned objects. The researchers built the framework using probabilistic programming, an AI approach that enables the system to cross-check detected objects against input data, to see if the images recorded from a camera are a likely match to any candidate scene.

Are there things that we must not know? This is an age-old question. Some assert that there is the potential for knowledge that ought to not be known. In other words, there are ideas, concepts, or mental formulations that should we become aware of that knowledge it could be our downfall. The discovery or invention of some new innovation or way of thinking could be unduly dangerous. It would be best to not go there, as it were, and avoid ever landing on such knowledge: forbidden knowledge.

Imagine that you are driving your car and come upon a dog that has suddenly darted into the roadway. Most of us have had this happen. You hopefully were able to take evasive action. Assuming that all went well, the pooch was fine and nobody in your car got hurt either. In a kind of Groundhog Day movie manner, let's repeat the scenario, but we will make a small change. Imagine that you are driving your car and come upon a deer that has suddenly darted into the roadway. Fewer of us have had this happen, though nonetheless, it is a somewhat common occurrence for those that live in a region that has deer aplenty.

Artificial intelligence researchers have not been successful in giving intelligent agents the common-sense knowledge they need to reason about the world. Without this knowledge, it is impossible for intelligent agents to truly interact with the world. Traditionally, there have been two unsuccessful approaches to getting computers to reason about the world--symbolic logic and deep learning. A new project, called COMET, tries to bring these two approaches together. Although it has not yet succeeded, it offers the possibility of progress.

Artificial intelligence researchers have not been successful in giving intelligent agents the common-sense knowledge they need to reason about the world. Without this knowledge, it is impossible for intelligent agents to truly interact with the world. Traditionally, there have been two unsuccessful approaches to getting computers to reason about the world--symbolic logic and deep learning. A new project, called COMET, tries to bring these two approaches together. Although it has not yet succeeded, it offers the possibility of progress.