Keith J. Holyoak

Taylor Webb, Keith J. Holyoak, Hongjing Lu

The recent advent of large language models has reinvigorated debate over whether human cognitive capacities might emerge in such generic models given sufficient training data. Of particular interest is the ability of these models to reason about novel problems zero-shot, without any direct training. In human cognition, this capacity is closely tied to an ability to reason by analogy. Here, we performed a direct comparison between human reasoners and a large language model (the text-davinci-003 variant of GPT-3) on a range of analogical tasks, including a non-visual matrix reasoning task based on the rule structure of Raven's Standard Progressive Matrices. We found that GPT-3 displayed a surprisingly strong capacity for abstract pattern induction, matching or even surpassing human capabilities in most settings; preliminary tests of GPT-4 indicated even better performance. Our results indicate that large language models such as GPT-3 have acquired an emergent ability to find zero-shot solutions to a broad range of analogy problems.

Nicholas Ichien, Dušan Stamenković, Keith J. Holyoak

Recent advances in the performance of large language models (LLMs) have sparked debate over whether, given sufficient training, high-level human abilities emerge in such generic forms of artificial intelligence (AI). Despite the exceptional performance of LLMs on a wide range of tasks involving natural language processing and reasoning, there has been sharp disagreement as to whether their abilities extend to more creative human abilities. A core example is the ability to interpret novel metaphors. Given the enormous and non curated text corpora used to train LLMs, a serious obstacle to designing tests is the requirement of finding novel yet high quality metaphors that are unlikely to have been included in the training data. Here we assessed the ability of GPT4, a state of the art large language model, to provide natural-language interpretations of novel literary metaphors drawn from Serbian poetry and translated into English. Despite exhibiting no signs of having been exposed to these metaphors previously, the AI system consistently produced detailed and incisive interpretations. Human judges, blind to the fact that an AI model was involved, rated metaphor interpretations generated by GPT4 as superior to those provided by a group of college students. In interpreting reversed metaphors, GPT4, as well as humans, exhibited signs of sensitivity to the Gricean cooperative principle. In addition, for several novel English poems GPT4 produced interpretations that were rated as excellent or good by a human literary critic. These results indicate that LLMs such as GPT4 have acquired an emergent ability to interpret complex metaphors, including those embedded in novel poems.

Taylor W. Webb, Shuhao Fu, Trevor Bihl et al.

Human reasoning is grounded in an ability to identify highly abstract commonalities governing superficially dissimilar visual inputs. Recent efforts to develop algorithms with this capacity have largely focused on approaches that require extensive direct training on visual reasoning tasks, and yield limited generalization to problems with novel content. In contrast, a long tradition of research in cognitive science has focused on elucidating the computational principles underlying human analogical reasoning; however, this work has generally relied on manually constructed representations. Here we present visiPAM (visual Probabilistic Analogical Mapping), a model of visual reasoning that synthesizes these two approaches. VisiPAM employs learned representations derived directly from naturalistic visual inputs, coupled with a similarity-based mapping operation derived from cognitive theories of human reasoning. We show that without any direct training, visiPAM outperforms a state-of-the-art deep learning model on an analogical mapping task. In addition, visiPAM closely matches the pattern of human performance on a novel task involving mapping of 3D objects across disparate categories.

Taylor Webb, Keith J. Holyoak, Hongjing Lu

We recently reported evidence that large language models are capable of solving a wide range of text-based analogy problems in a zero-shot manner, indicating the presence of an emergent capacity for analogical reasoning. Two recent commentaries have challenged these results, citing evidence from so-called `counterfactual' tasks in which the standard sequence of the alphabet is arbitrarily permuted so as to decrease similarity with materials that may have been present in the language model's training data. Here, we reply to these critiques, clarifying some misunderstandings about the test materials used in our original work, and presenting evidence that language models are also capable of generalizing to these new counterfactual task variants.

Andrew Jun Lee, Taylor Webb, Trevor Bihl et al.

The ability to learn new visual concepts from limited examples is a hallmark of human cognition. While traditional category learning models represent each example as an unstructured feature vector, compositional concept learning is thought to depend on (1) structured representations of examples (e.g., directed graphs consisting of objects and their relations) and (2) the identification of shared relational structure across examples through analogical mapping. Here, we introduce Probabilistic Schema Induction (PSI), a prototype model that employs deep learning to perform analogical mapping over structured representations of only a handful of examples, forming a compositional concept called a schema. In doing so, PSI relies on a novel conception of similarity that weighs object-level similarity and relational similarity, as well as a mechanism for amplifying relations relevant to classification, analogous to selective attention parameters in traditional models. We show that PSI produces human-like learning performance and outperforms two controls: a prototype model that uses unstructured feature vectors extracted from a deep learning model, and a variant of PSI with weaker structured representations. Notably, we find that PSI's human-like performance is driven by an adaptive strategy that increases relational similarity over object-level similarity and upweights the contribution of relations that distinguish classes. These findings suggest that structured representations and analogical mapping are critical to modeling rapid human-like learning of compositional visual concepts, and demonstrate how deep learning can be leveraged to create psychological models.

Nicholas Ichien, Qing Liu, Shuhao Fu et al.

Is analogical reasoning a task that must be learned to solve from scratch by applying deep learning models to massive numbers of reasoning problems? Or are analogies solved by computing similarities between structured representations of analogs? We address this question by comparing human performance on visual analogies created using images of familiar three-dimensional objects (cars and their subregions) with the performance of alternative computational models. Human reasoners achieved above-chance accuracy for all problem types, but made more errors in several conditions (e.g., when relevant subregions were occluded). We compared human performance to that of two recent deep learning models (Siamese Network and Relation Network) directly trained to solve these analogy problems, as well as to that of a compositional model that assesses relational similarity between part-based representations. The compositional model based on part representations, but not the deep learning models, generated qualitative performance similar to that of human reasoners.

Hongjing Lu, Nicholas Ichien, Keith J. Holyoak

The human ability to flexibly reason using analogies with domain-general content depends on mechanisms for identifying relations between concepts, and for mapping concepts and their relations across analogs. Building on a recent model of how semantic relations can be learned from non-relational word embeddings, we present a new computational model of mapping between two analogs. The model adopts a Bayesian framework for probabilistic graph matching, operating on semantic relation networks constructed from distributed representations of individual concepts and of relations between concepts. Through comparisons of model predictions with human performance in a novel mapping task requiring integration of multiple relations, as well as in several classic studies, we demonstrate that the model accounts for a broad range of phenomena involving analogical mapping by both adults and children. We also show the potential for extending the model to deal with analog retrieval. Our approach demonstrates that human-like analogical mapping can emerge from comparison mechanisms applied to rich semantic representations of individual concepts and relations.