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.

Few shot classification aims to learn to recognize novel categories using only limited samples per category. Most current few shot methods use a base dataset rich in labeled examples to train an encoder that is used for obtaining representations of support instances for novel classes. Since the test instances are from a distribution different to the base distribution, their feature representations are of poor quality, degrading performance. In this paper we propose to make use of the well-trained feature representations of the base dataset that are closest to each support instance to improve its representation during meta-test time. To this end, we propose BaseTransformers, that attends to the most relevant regions of the base dataset feature space and improves support instance representations. Experiments on three benchmark data sets show that our method works well for several backbones and achieves state-of-the-art results in the inductive one shot setting. Code is available at github.com/mayug/BaseTransformers

In the abundance of information, both machines and human researchers need tools to navigate and process it. Structuring and formalization of data into hierarchies, such as trees, may establish the relations between the data required for efficient machine processing and may make the information more readable for data analysts. Yet, in more complex domains, such as in natural language processing, relations between concepts go beyond simple hierarchies and form thesaurus-like networks. For such cases, researchers use ontologies as common vocabularies for specialists who need to share information in a domain. Ontologies were first defined as "explicit formal specifications of the terms in the domain and relations among them" (Gruber 1993) and, more specifically, "a formal, explicit specification of a shared conceptualization" (Studer et al. 1998) and are used in a number of applications, including the following, as specified by Noy and McGuinness (Noy and McGuinness 2001): Ontologies are the tools to provide comprehensive description of the domain of interest with respect to the users' needs It is something that we see when, for example, medical information is published on, several different websites.

The coronavirus pandemic has been an eye-opener for capital markets firms hit by market volatility, systems unable to cope quickly with change, the need to set up work from home schemes (and security), and changing relationships with customers. Nowhere has this been more visible than in Know Your Customer (KYC) and onboarding functions that have been pushed to accelerate digitalisation, pare down document exchange (again), and reconsider optimal operating models. As well as providing a response to the pandemic, these changes are helping firms look to the future. Kevin McGuinness, client lifecycle management lead at First Derivatives, suggests capital markets participants have coped well with the pandemic, although it has raised the bar. He says: "Covid has made it clear that there is still room to reduce the friction between banks and customers. Getting data back and forth requires better solutions and the ultimate goal has to be no paper."

In the abundance of information, both machines and human researchers need tools to navigate and process it. Structuring and formalization of data into hierarchies, such as trees, may establish the relations between the data required for efficient machine processing and may make the information more readable for data analysts. Yet, in more complex domains, such as in natural language processing, relations between concepts go beyond simple hierarchies and form thesaurus-like networks. For such cases, researchers use ontologies as common vocabularies for specialists who need to share information in a domain. Ontologies were first defined as "explicit formal specifications of the terms in the domain and relations among them" (Gruber 1993) and, more specifically, "a formal, explicit specification of a shared conceptualization" (Studer et al. 1998) and are used in a number of applications, including the following, as specified by Noy and McGuinness (Noy and McGuinness 2001): Ontologies are the tools to provide comprehensive description of the domain of interest with respect to the users' needs It is something that we see when, for example, medical information is published on, several different websites.

Explainability has been an important goal since the early days of Artificial Intelligence. Several approaches for producing explanations have been developed. However, many of these approaches were tightly coupled with the capabilities of the artificial intelligence systems at the time. With the proliferation of AI-enabled systems in sometimes critical settings, there is a need for them to be explainable to end-users and decision-makers. We present a historical overview of explainable artificial intelligence systems, with a focus on knowledge-enabled systems, spanning the expert systems, cognitive assistants, semantic applications, and machine learning domains. Additionally, borrowing from the strengths of past approaches and identifying gaps needed to make explanations user- and context-focused, we propose new definitions for explanations and explainable knowledge-enabled systems.

One primary task of population health analysis is the identification of risk factors that, for some subpopulation, have a significant association with some health condition. Examples include finding lifestyle factors associated with chronic diseases and finding genetic mutations associated with diseases in precision health. We develop a combined semantic and machine learning system that uses a health risk ontology and knowledge graph (KG) to dynamically discover risk factors and their associated subpopulations. Semantics and the novel supervised cadre model make our system explainable. Future population health studies are easily performed and documented with provenance by specifying additional input and output KG cartridges.

The need for access to and interoperability between these repositories is growing. Research groups need to access their own increasingly diverse data collections. As investigations begin to include results from many different experiments, researchers also need to access and utilize other research groups' data repositories in a single discipline or, more interestingly, in multiple disciplines. Also, it is not simply trained scientists who are interested in accessing scientific data; lay people are becoming interested in looking at trends in scientific data as well, for example, when they become engaged in climate discussions. The promise of the true virtual interconnected heterogeneous distributed international data repository is starting to be realized.

The General Motors Variation-Reduction Adviser is a knowledge system built on case-based reasoning principles that is currently in use in eighteen General Motors asssembly centers. This article reviews the overall characteristics of the system and then focuses on various AI elements critical to support its deployment to a production system. A key AI enabler is ontology-guided search using domainspecific ontologies. The primary use of VRA is to improve communication in the plants and between plants to assist with problem solving necessary to keep the line producing the highest quality products. Our original prototype was tested by a "dimensional management" team working on "variation reduction" problems in a plant.

This is an updated version of Usability Issues in Description Logic Systems'' published in Proceedings of International Workshop on Description Logics, Gif sur Yvette, (Paris), France, September, 1997.