Neural Information Processing Systems http://nips.cc/

This paper investigates visual analogical reasoning in large multimodal models (LMMs) compared to human adults and children. A "visual analogy" is an abstract rule inferred from one image and applied to another. While benchmarks exist for testing visual reasoning in LMMs, they require advanced skills and omit basic visual analogies that even young children can make. Inspired by developmental psychology, we propose a new benchmark of 1,400 visual transformations of everyday objects to test LMMs on visual analogical reasoning and compare them to children and adults. We structure the evaluation into three stages: identifying what changed (e.g., color, number, etc.), how it changed (e.g., added one object), and applying the rule to new scenarios. Our findings show that while models like GPT-4V, LLaVA-1.5, and MANTIS identify the "what" effectively, they struggle with quantifying the "how" and extrapolating this rule to new objects. In contrast, children and adults exhibit much stronger analogical reasoning at all three stages. Additionally, the strongest tested model, GPT-4V, performs better in tasks involving simple visual attributes like color and size, correlating with quicker human adult response times. Conversely, more complex tasks such as number, rotation, and reflection, which necessitate extensive cognitive processing and understanding of the 3D physical world, present more significant challenges. Altogether, these findings highlight the limitations of training models on data that primarily consists of 2D images and text.

As an embodied and spatial medium, virtual reality is proving an attractive proposition for robot teleoperation in hazardous environments. This paper examines a nuclear decommissioning scenario in which a simulated team of semi-autonomous robots are used to characterise a chamber within a virtual nuclear facility. This study examines the potential utility and impact of sonification as a means of communicating salient operator data in such an environment. However, the question of what sound should be used and how it can be applied in different applications is far from resolved. This paper explores and compares two sonification design approaches. The first is inspired by the theory of cognitive metaphor to create sonifications that align with socially acquired contextual and ecological understanding of the application domain. The second adopts a computationalist approach using auditory mappings that are commonplace in the literature. The results suggest that the computationalist approach outperforms the cognitive metaphor approach in terms of predictability and mental workload. However, qualitative data analysis demonstrates that the cognitive metaphor approach resulted in sounds that were more intuitive, and were better implemented for spatialisation of data sources and data legibility when there was more than one sound source.

Analogical reasoning is the ability to detect parallels between two seemingly distant objects or situations, a fundamental human capacity used for example in commonsense reasoning, learning, and creativity which is believed by many researchers to be at the core of human and artificial general intelligence. Analogical proportions are expressions of the form ``$a$ is to $b$ what $c$ is to $d$'' at the core of analogical reasoning. The author has recently introduced an abstract algebraic framework of analogical proportions within the general setting of universal algebra. It is the purpose of this paper to further develop the mathematical theory of analogical proportions within that framework as motivated by the fact that it has already been successfully applied to logic program synthesis in artificial intelligence.

With our work, we contribute towards a qualitative analysis of the discourse on controversies in online news media. For this, we employ Formal Concept Analysis and the economics of conventions to derive conceptual controversy maps. In our experiments, we analyze two maps from different news journals with methods from ordinal data science. We show how these methods can be used to assess the diversity, complexity and potential bias of controversies. In addition to that, we discuss how the diagrams of concept lattices can be used to navigate between news articles.

Analogical reasoning is one of the prime abilities of humans and is linked to creativity and scientific discoveries. This ability has been studied extensively in natural language processing (NLP) and in cognitive psychology. NLP benchmarks often focus on proportional analogies, while the ones in cognitive psychology investigate longer pieces of text too. Yet, although studies that focus on analogical reasoning in an involved setting utilize narratives as their evaluation medium, analogical reasoning on narratives has not been studied extensively. We create an extensive evaluation framework for analogical reasoning on narratives that utilizes narrative elements to create lower-order and higher-order mappings that subsequently lead to the development of the Analogical Reasoning on Narratives (ARN) benchmark that covers four categories of far(cross-domain)/near(within-domain) analogies and far/near disanalogies, allowing us to study analogical reasoning in LLMs in distinct scenarios. Our results demonstrate that LLMs struggle to recognize higher-order mappings when they are not accompanied by lower-order mappings (far analogies) and show better performance when all mappings are formed simultaneously (near analogies). We observe that in all the scenarios, the analogical reasoning abilities of LLMs can be easily impaired by lower-order mappings in near disanalogies.

Analogy is one of the core capacities of human cognition; when faced with new situations, we often transfer prior experience from other domains. Most work on computational analogy relies heavily on complex, manually crafted input. In this work, we relax the input requirements, requiring only names of entities to be mapped. We automatically extract commonsense representations and use them to identify a mapping between the entities. Unlike previous works, our framework can handle partial analogies and suggest new entities to be added. Moreover, our method's output is easily interpretable, allowing for users to understand why a specific mapping was chosen. Experiments show that our model correctly maps 81.2% of classical 2x2 analogy problems (guess level=50%). On larger problems, it achieves 77.8% accuracy (mean guess level=13.1%). In another experiment, we show our algorithm outperforms human performance, and the automatic suggestions of new entities resemble those suggested by humans. We hope this work will advance computational analogy by paving the way to more flexible, realistic input requirements, with broader applicability.

While analogies are a common way to evaluate word embeddings in NLP, it is also of interest to investigate whether or not analogical reasoning is a task in itself that can be learned. In this paper, we test several ways to learn basic analogical reasoning, specifically focusing on analogies that are more typical of what is used to evaluate analogical reasoning in humans than those in commonly used NLP benchmarks. Our experiments find that models are able to learn analogical reasoning, even with a small amount of data. We additionally compare our models to a dataset with a human baseline, and find that after training, models approach human performance.

Metaphorically speaking, there is a wide river between computer-based data analysis methods on one side and Cognitive Linguistics (CL) and especially Conceptual Metaphor Theory (CMT) on the other side. Every now and then, a small boat attempts to cross this river, but our goal is to build a solid and lasting bridge. Less metaphorically, we need and want to address two different research communities simultaneously, each with its own concepts, ways of thinking and arguing, and discursive practices. To metaphor research, we present a statistical, data-based investigation that empirically analyzes long-standing conjectures and provides the first-ever exploration of the systematic structure underlying metaphors. To the Natural Language Processing community, we introduce metaphor theory as a basis of meaning emergence that can be quantitatively explored and whose understanding and integration into NLP methodologies hold great potential. Cognitive Linguistics and Data Analysis Data driven linguistics is a very active and lively research field, but there exists a blind spot regarding the findings of Cognitive Linguistics [1, 2] (CL for short). CL is an actively developing branch of linguistics without an established closed canon. It depends on several widely accepted premises.

Analogical reasoning is a fundamental capacity of human cognition that allows us to reason abstractly about novel situations by relating them to past experiences. While it is thought to be essential for robust reasoning in AI systems, conventional approaches require significant training and/or hard-coding of domain knowledge to be applied to benchmark tasks. Inspired by cognitive science research that has found connections between human language and analogy-making, we explore the use of intuitive language-based abstractions to support analogy in AI systems. Specifically, we apply large pre-trained language models (PLMs) to visual Raven's Progressive Matrices (RPM), a common relational reasoning test. By simply encoding the perceptual features of the problem into language form, we find that PLMs exhibit a striking capacity for zero-shot relational reasoning, exceeding human performance and nearing supervised vision-based methods. We explore different encodings that vary the level of abstraction over task features, finding that higher-level abstractions further strengthen PLMs' analogical reasoning. Our detailed analysis reveals insights on the role of model complexity, in-context learning, and prior knowledge in solving RPM tasks.