Generative large language models (LLMs) have transformed AI by enabling rapid, human-like text generation, but they face challenges, including managing inaccurate information generation. Strategies such as prompt engineering, Retrieval-Augmented Generation (RAG), and incorporating domain-specific Knowledge Graphs (KGs) aim to address their issues. However, challenges remain in achieving the desired levels of management, repeatability, and verification of experiments, especially for developers using closed-access LLMs via web APIs, complicating integration with external tools. To tackle this, we are exploring a software architecture to enhance LLM workflows by prioritizing flexibility and traceability while promoting more accurate and explainable outputs. We describe our approach and provide a nutrition case study demonstrating its ability to integrate LLMs with RAG and KGs for more robust AI solutions.

Recent research has revealed that many machine-learning models and the datasets they are trained on suffer from various forms of bias, and a large number of different fairness metrics have been created to measure this bias. However, determining which metrics to use, as well as interpreting their results, is difficult for a non-expert due to a lack of clear guidance and issues of ambiguity or alternate naming schemes between different research papers. To address this knowledge gap, we present the Fairness Metrics Ontology (FMO), a comprehensive and extensible knowledge resource that defines each fairness metric, describes their use cases, and details the relationships between them. We include additional concepts related to fairness and machine learning models, enabling the representation of specific fairness information within a resource description framework (RDF) knowledge graph. We evaluate the ontology by examining the process of how reasoning-based queries to the ontology were used to guide the fairness metric-based evaluation of a synthetic data model.

The rapidly decreasing cost of gene sequencing has resulted in a deluge of genomic data from across the tree of life; however, outside a few model organism databases, genomic data are limited in their scientific impact because they are not accompanied by computable phenomic data. The majority of phenomic data are contained in countless small, heterogeneous phenotypic data sets that are very difficult or impossible to integrate at scale because of variable formats, lack of digitization, and linguistic problems. One powerful solution is to represent phenotypic data using data models with precise, computable semantics, but adoption of semantic standards for representing phenotypic data has been slow, especially in biodiversity and ecology. Some phenotypic and trait data are available in a semantic language from knowledge bases, but these are often not interoperable. In this review, we will compare and contrast existing ontology and data models, focusing on nonhuman phenotypes and traits. We discuss barriers to integration of phenotypic data and make recommendations for developing an operationally useful, semantically interoperable phenotypic data ecosystem.

Analysts who are interested in quickly identifying new and emerging scientific advancements have numerous challenges as the breadth, depth, and volume of scientific literature increases. Network analysis and mining is key to the success in this task. The ARBITER system seeks to identify indicators of emergence and provide a system that is capable of analyzing corpora of full text and metadata to identify emerging science topics and explain its reasoning and conclusions. In this paper, we describe a network-modeling framework that is used in the ARBITER system, and describe our novel hybrid approach using probabilistic foundations in combination with semantic technology and introduce our explanation infrastructure. We include a discussion of some challenges and opportunities related to explaining hybrid approaches to indicator-based analysis and emergence detection.

The important topic of global climate change builds on a huge collection of scientific research. It is common for agencies releasing climate change information to be served with requests for all supporting materials resulting in a particular conclusion. Capturing and presenting global change provenance, linking to the research papers, data sets, models, analyses, observations, satellites, etc., that support the key research findings in this domain can increase understanding and aid in reproducibility of results and conclusions. The U.S. Global Change Research Program is now coordinating the production of a national climate assessment (NCA) that presents our best understanding of global change. We are now developing a global change information system that will present the content of that report and its provenance, including the scientific support for the findings of the assessment. We are using an approach that will present this information both through a human accessible Web site as well as a machine-readable interface for automated mining of the provenance graph. We plan to use the developing World Wide Web Consortium (W3C) PROV data model and ontology for this system. This paper will describe an overview of the process of developing the NCA and how the provenance trail of the report and each of the technical inputs can be captured and represented using the W3C PROV ontology. This will improve the visibility into the assessment process, increase understanding and possibility of reproducibility, and ultimately increase the credibility and trust of the resulting report.

We aim to inform the development of decision support tools for resource managers who need to examine large complex ecosystems and make recommendations in the face of many tradeoffs and conflicting drivers. We take a semantic technology approach, leveraging background ontologies and the growing body of open linked data. In previous work, we designed and implemented a semantically-enabled environmental monitoring framework called SemantEco and used it to build a water quality portal named SemantAqua. In this work, we significantly extend SemantEco to include knowledge required to support resource decisions concerning fish and wildlife species and their habitats. Our previous system included foundational ontologies to support environmental regulation violations and relevant human health effects. Our enhanced framework includes foundational ontologies to support modeling of wildlife observation and wildlife health impacts, thereby enabling deeper and broader support for more holistically examining the effects of environmental pollution on ecosystems. Our results include a refactored and expanded version of the SemantEco portal. Additionally the updated system is now compatible with the emerging best in class Extensible Observation Ontology (OBOE). A wider range of relevant data has been integrated, focusing on additions concerning wildlife health related to exposure to contaminants. The resulting system stores and exposes provenance concerning the source of the data, how it was used, and also the rationale for choosing the data. In this paper, we describe the system, highlight its research contributions, and describe current and envisioned usage.

We present a novel ensemble architecture for learning problem-solving techniques from a very small number of expert solutions and demonstrate its effectiveness in a complex real-world domain. The key feature of our “Generalized Integrated Learning Architecture” (GILA) is a set of heterogeneous independent learning and reasoning (ILR) components, coordinated by a central meta-reasoning executive (MRE). The ILRs are weakly coupled in the sense that all coordination during learning and performance happens through the MRE. Each ILR learns independently from a small number of expert demonstrations of a complex task. During performance, each ILR proposes partial solutions to subproblems posed by the MRE, which are then selected from and pieced together by the MRE to produce a complete solution. The heterogeneity of the learner-reasoners allows both learning and problem solving to be more effective because their abilities and biases are complementary and synergistic. We describe the application of this novel learning and problem solving architecture to the domain of airspace management, where multiple requests for the use of airspaces need to be deconflicted, reconciled, and managed automatically. Formal evaluations show that our system performs as well as or better than humans after learning from the same training data. Furthermore, GILA outperforms any individual ILR run in isolation, thus demonstrating the power of the ensemble architecture for learning and problem solving.

In many data-centric semantic web applications, it is desirable to use OWL to encode the Integrity Constraints (IC) that must be satisfied by instance data. However, challenges arise due to the Open World Assumption (OWA) and the lack of a Unique Name Assumption (UNA) in OWL’s standard semantics. In particular, conditions that trigger constraint violations in systems using the ClosedWorld Assumption (CWA), will generate new inferences in standard OWL-based reasoning applications. In this paper, we present an alternative IC semantics for OWL that allows applications to work with the CWA and the weak UNA. Ontology modelers can choose which OWL axioms to be interpreted with our IC semantics. Thus application developers are able to combine open world reasoning with closed world constraint validation in a flexible way. We also show that IC validation can be reduced to query answering under certain conditions. Finally, we describe our prototype implementation based on the OWL reasoner Pellet.

The Open Government Directive is making US government data available via websites such as Data.gov for public access. In this paper, we present a Semantic Web based approach that incrementally generates Linked Government Data (LGD) for the US government. In focusing on the trade-off between high quality LGD generation (requiring non-trivial human expert input) and massive LGD generation (requiring low human processing cost), our work is highlighted by the following features: (i) supporting low-cost and extensible LGD publishing for massive government data; (ii) using Social Semantic Web (Web3.0) technologies to incrementally enhance published LGD via crowdsourcing, and (iii) facilitating mash-ups by declaratively reusing cross-dataset mappings which usually are hard-coded in applications.

We consider the problem of supporting intuitive explanations in recommender systems used for automated career counseling. Explanations enhance the transparency in operation of a recommender system and facilitate user-acceptance, adoption, and trust in the system. We leverage the inference Web (IW) Infrastructure and the proof markup language (PML) as a foundation for supporting intuitive explanations in recommender systems for automated career counseling. We present the design and implementation of our system, highlighting the salient features of our approach using an illustrative example.

As adaptive agents become more complex and take increasing autonomy in their user's lives, it becomes more important for users to trust and understand these agents. Little work has been done, however, to study what factors influence the level of trust users are willing to place in these agents. Without trust in the actions and results produced by these agents, their use and adoption as trusted assistants and partners will be severely limited. We present the results of a study among test users of CALO, one such complex adaptive agent system, to investigate themes surrounding trust and understandability. We identify and discuss eight major themes that significantly impact user trust in complex systems. We further provide guidelines for the design of trustable adaptive agents. Based on our analysis of these results, we conclude that the availability of explanation capabilities in these agents can address the majority of trust concerns identified by users.

Many emerging semantic web applications include ontologies from one set of authors and instance data from another (often much larger) set of authors. Often ontologies are reused and instance data is integrated in manners unanticipated by their authors. Not surprisingly, many instance data rich applications encounter instance data that is not compatible with the expectations of the original ontology author(s). This line of work focuses on issues related to semantic expectation mismatches in instance data. Our initial results include a customizable and extensible service-oriented evaluation architecture, and a domain implementation called PmlValidator, which checks instance data using the corresponding ontologies and additional style requirements.

Wikis are a type of collaborative repository system that enables users to create and edit shared content on the Web. The popularity and proliferation of Wikis have created a new set of challenges for trust research because the content in a Wiki can be contributed by a wide variety of users and can change rapidly. Nevertheless, most Wikis lack explicit trust management to help users decide how much they should trust an article or a fragment of an article. In this paper, we investigate the dynamic nature of revisions as we explore ways of utilizing revision history to develop an article fragment trust model. We use our model to compute trustworthiness of articles and article fragments. We also augment Wikis with a trust view layer with which users can visually identify text fragments of an article and view trust values computed by our model

No abstract available.

Matching concepts against patterns (concepts with variables) is a relatively new operation that has been introduced in the context of concept description languages (description logics). The original goal was to help filter out unimportant aspects of complicated concepts appearing in large industrial knowledge bases. We propose a new approach to performing matching, based on a 'concept-centred' normal form, rather than the more standard 'structural subsumption' normal form for concepts. As a result, matching can be performed (in polynomial time) using arbitrary concept patterns of the description language ALN, thus removing restrictions from previous work. The paper also addresses the question of matching problems with additional 'side conditions', which were motivated by practical needs. Key words: Knowledge representation, description logics, matching.

E Franconi, G De Giacomo, IR Horrocks, DL McGuinness, W Nutt, PF Patel-Schneider, CA Welty; Conferences. Report on the 1998 International Workshop on Descriptio

Corporate databases increasingly are being viewed as potentially rich sources of new and valuable knowledge. Various approaches to “discovering” or “mining” such knowledge have been proposed. Here we identify an important and previously ignored discovery task, which we call data archaeology. Data archaeology is a skilled human task, in which the knowledge sought depends on the goals of the analyst, cannot be specified in advance, and emerges only through an iterative process of data segmentation and analysis. We describe a system that supports the data archaeologist with a natural, object-oriented representation of an application domain, a powerful query language and database translation routines, and an easy-to-use and flexible user interface that supports interactive exploration. A formal knowledge representation system provides the core technology that facilitates database integration, querying, and the reuse of queries and query results.

CLASSIC is a data model that encourages the description of objects not only in terms of their relations to other known objects, but in terms of a level of intensional structure as well. The CLASSIC language of structured descriptions permits i) partial descriptions of individuals, under an 'open world' assumption, ii) answers to queries either as extensional lists of values or as descriptions that necessarily hold of all possible answers, and iii) an easily extensible schema, which can be accessed uniformly with the data. One of the strengths of the approach is that the same language plays multiple roles in the processes of defining and populating the DB, as well as querying and answering.

Knowledge Representation (KR) systems provide support for Artificial Intelligence systems that reason about relationships between objects in their domains of expertise. Because of their support for inference, KR systems appear to have potential to enrich the kind of retrievals that IR systems might make. Ironically, however, the most useful KR systems are limited to reasoning based on a rigid notion of validity, and thus are awkward to use when relevant but inexact retrievals are desired. We have been exploring the potential of a “connectionist” model—the Boltzmann Machine—to overcome this limitation. We report on a number of experiments in which we use a connectionist simulator to support similarity-based reasoning in a frame representation. We draw some tentative, mixed conclusions on the potential for a union of KR, IR, and connectionism.