Deborah L. McGuinness

Shruthi Chari, Prasant Acharya, Daniel M. Gruen et al. · stanford

Medical experts may use Artificial Intelligence (AI) systems with greater trust if these are supported by contextual explanations that let the practitioner connect system inferences to their context of use. However, their importance in improving model usage and understanding has not been extensively studied. Hence, we consider a comorbidity risk prediction scenario and focus on contexts regarding the patients clinical state, AI predictions about their risk of complications, and algorithmic explanations supporting the predictions. We explore how relevant information for such dimensions can be extracted from Medical guidelines to answer typical questions from clinical practitioners. We identify this as a question answering (QA) task and employ several state-of-the-art LLMs to present contexts around risk prediction model inferences and evaluate their acceptability. Finally, we study the benefits of contextual explanations by building an end-to-end AI pipeline including data cohorting, AI risk modeling, post-hoc model explanations, and prototyped a visual dashboard to present the combined insights from different context dimensions and data sources, while predicting and identifying the drivers of risk of Chronic Kidney Disease - a common type-2 diabetes comorbidity. All of these steps were performed in engagement with medical experts, including a final evaluation of the dashboard results by an expert medical panel. We show that LLMs, in particular BERT and SciBERT, can be readily deployed to extract some relevant explanations to support clinical usage. To understand the value-add of the contextual explanations, the expert panel evaluated these regarding actionable insights in the relevant clinical setting. Overall, our paper is one of the first end-to-end analyses identifying the feasibility and benefits of contextual explanations in a real-world clinical use case.

Henrique Santos, Ke Shen, Alice M. Mulvehill et al. · stanford

Programming machines with commonsense reasoning (CSR) abilities is a longstanding challenge in the Artificial Intelligence community. Current CSR benchmarks use multiple-choice (and in relatively fewer cases, generative) question-answering instances to evaluate machine commonsense. Recent progress in transformer-based language representation models suggest that considerable progress has been made on existing benchmarks. However, although tens of CSR benchmarks currently exist, and are growing, it is not evident that the full suite of commonsense capabilities have been systematically evaluated. Furthermore, there are doubts about whether language models are 'fitting' to a benchmark dataset's training partition by picking up on subtle, but normatively irrelevant (at least for CSR), statistical features to achieve good performance on the testing partition. To address these challenges, we propose a benchmark called Theoretically-Grounded Commonsense Reasoning (TG-CSR) that is also based on discriminative question answering, but with questions designed to evaluate diverse aspects of commonsense, such as space, time, and world states. TG-CSR is based on a subset of commonsense categories first proposed as a viable theory of commonsense by Gordon and Hobbs. The benchmark is also designed to be few-shot (and in the future, zero-shot), with only a few training and validation examples provided. This report discusses the structure and construction of the benchmark. Preliminary results suggest that the benchmark is challenging even for advanced language representation models designed for discriminative CSR question answering tasks. Benchmark access and leaderboard: https://codalab.lisn.upsaclay.fr/competitions/3080 Benchmark website: https://usc-isi-i2.github.io/TGCSR/

Devin Yasith De Silva, Dhaval Patel, Christodoulos Constantinides et al.

Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perform corrective actions. The bottleneck is not detection but response: translating rules into maintenance steps requires asset-specific knowledge gained through years of practice. We investigate whether LLMs can serve as decision support for this rule-to-action step and introduce \ours{}, a benchmark of 6{,}690 expert-validated multiple-choice questions from 118 rule-action pairs across 16 asset types. We contribute (i) a symbolic-to-MCQA pipeline normalizing rules to Disjunctive Normal Form with embedding-based distractor sampling, (ii) five variants probing distinct failure modes (Pro, Pert, Verbose, Aug, Rationale), and (iii) a benchmark of 29 LLMs and 4 embedding baselines. A human evaluation (9 practitioners, mean 45.0\%) confirms \ours{} requires specialist knowledge beyond operational experience. Three findings stand out. The frontier has closed: the top three LLMs lie within one Macro point, with Bradley-Terry Elo placing claude-opus-4-6 30 points above the next model. Yet \ours{}\,Pro exposes brittleness, with every model losing 13--60\% relative accuracy under distractor expansion. \ours{}\,Aug exposes pattern-matching: under condition inversion, frontier models still select the original answer 49--63\% of the time. The deployment bottleneck is not capability but calibration: frontier models handle template-style fault detection but break under structural perturbation.

Shruthi Chari, Oshani Seneviratne, Prithwish Chakraborty et al.

Explanations are crucial for building trustworthy AI systems, but a gap often exists between the explanations provided by models and those needed by users. To address this gap, we introduce MetaExplainer, a neuro-symbolic framework designed to generate user-centered explanations. Our approach employs a three-stage process: first, we decompose user questions into machine-readable formats using state-of-the-art large language models (LLM); second, we delegate the task of generating system recommendations to model explainer methods; and finally, we synthesize natural language explanations that summarize the explainer outputs. Throughout this process, we utilize an Explanation Ontology to guide the language models and explainer methods. By leveraging LLMs and a structured approach to explanation generation, MetaExplainer aims to enhance the interpretability and trustworthiness of AI systems across various applications, providing users with tailored, question-driven explanations that better meet their needs. Comprehensive evaluations of MetaExplainer demonstrate a step towards evaluating and utilizing current state-of-the-art explanation frameworks. Our results show high performance across all stages, with a 59.06% F1-score in question reframing, 70% faithfulness in model explanations, and 67% context-utilization in natural language synthesis. User studies corroborate these findings, highlighting the creativity and comprehensiveness of generated explanations. Tested on the Diabetes (PIMA Indian) tabular dataset, MetaExplainer supports diverse explanation types, including Contrastive, Counterfactual, Rationale, Case-Based, and Data explanations. The framework's versatility and traceability from using ontology to guide LLMs suggest broad applicability beyond the tested scenarios, positioning MetaExplainer as a promising tool for enhancing AI explainability across various domains.

Piero A. Bonatti, John Domingue, Anna Lisa Gentile et al.

Computer-Using Agents (CUA) enable users to automate increasingly-complex tasks using graphical interfaces such as browsers. As many potential tasks require personal data, we propose Computer-Using Personal Agents (CUPAs) that have access to an external repository of the user's personal data. Compared with CUAs, CUPAs offer users better control of their personal data, the potential to automate more tasks involving personal data, better interoperability with external sources of data, and better capabilities to coordinate with other CUPAs in order to solve collaborative tasks involving the personal data of multiple users.

Oshani Seneviratne, Jonathan Harris, Ching-Hua Chen et al.

We propose a knowledge model for capturing dietary preferences and personal context to provide personalized dietary recommendations. We develop a knowledge model called the Personal Health Ontology, which is grounded in semantic technologies, and represents a patient's combined medical information, social determinants of health, and observations of daily living elicited from interviews with diabetic patients. We then generate a personal health knowledge graph that captures temporal patterns from synthetic food logs, annotated with concepts from the Personal Health Ontology. We further discuss how lifestyle guidelines grounded in semantic technologies can be reasoned with the generated personal health knowledge graph to provide appropriate dietary recommendations that satisfy the user's medical and other lifestyle needs.

Shruthi Chari, Prithwish Chakraborty, Mohamed Ghalwash et al.

Academic advances of AI models in high-precision domains, like healthcare, need to be made explainable in order to enhance real-world adoption. Our past studies and ongoing interactions indicate that medical experts can use AI systems with greater trust if there are ways to connect the model inferences about patients to explanations that are tied back to the context of use. Specifically, risk prediction is a complex problem of diagnostic and interventional importance to clinicians wherein they consult different sources to make decisions. To enable the adoption of the ever improving AI risk prediction models in practice, we have begun to explore techniques to contextualize such models along three dimensions of interest: the patients' clinical state, AI predictions about their risk of complications, and algorithmic explanations supporting the predictions. We validate the importance of these dimensions by implementing a proof-of-concept (POC) in type-2 diabetes (T2DM) use case where we assess the risk of chronic kidney disease (CKD) - a common T2DM comorbidity. Within the POC, we include risk prediction models for CKD, post-hoc explainers of the predictions, and other natural-language modules which operationalize domain knowledge and CPGs to provide context. With primary care physicians (PCP) as our end-users, we present our initial results and clinician feedback in this paper. Our POC approach covers multiple knowledge sources and clinical scenarios, blends knowledge to explain data and predictions to PCPs, and received an enthusiastic response from our medical expert.

Henrique Santos, James P. McCusker, Deborah L. McGuinness

Policies are authoritative assets that are present in multiple domains to support decision-making. They describe what actions are allowed or recommended when domain entities and their attributes satisfy certain criteria. It is common to find policies that contain geographical rules, including distance and containment relationships among named locations. These locations' polygons can often be found encoded in geospatial datasets. We present an approach to transform data from geospatial datasets into Linked Data using the OWL, PROV-O, and GeoSPARQL standards, and to leverage this representation to support automated ontology-based policy decisions. We applied our approach to location-sensitive radio spectrum policies to identify relationships between radio transmitters coordinates and policy-regulated regions in Census.gov datasets. Using a policy evaluation pipeline that mixes OWL reasoning and GeoSPARQL, our approach implements the relevant geospatial relationships, according to a set of requirements elicited by radio spectrum domain experts.

Ishita Padhiar, Oshani Seneviratne, Shruthi Chari et al.

With the increased use of AI methods to provide recommendations in the health, specifically in the food dietary recommendation space, there is also an increased need for explainability of those recommendations. Such explanations would benefit users of recommendation systems by empowering them with justifications for following the system's suggestions. We present the Food Explanation Ontology (FEO) that provides a formalism for modeling explanations to users for food-related recommendations. FEO models food recommendations, using concepts from the explanation domain to create responses to user questions about food recommendations they receive from AI systems such as personalized knowledge base question answering systems. FEO uses a modular, extensible structure that lends itself to a variety of explanations while still preserving important semantic details to accurately represent explanations of food recommendations. In order to evaluate this system, we used a set of competency questions derived from explanation types present in literature that are relevant to food recommendations. Our motivation with the use of FEO is to empower users to make decisions about their health, fully equipped with an understanding of the AI recommender systems as they relate to user questions, by providing reasoning behind their recommendations in the form of explanations.

Sola Shirai, Oshani Seneviratne, Deborah L. McGuinness

Knowledge graphs that encapsulate personal health information, or personal health knowledge graphs (PHKG), can help enable personalized health care in knowledge-driven systems. In this paper we provide a short survey of existing work surrounding the emerging paradigm of PHKGs and highlight the major challenges that remain. We find that while some preliminary exploration exists on the topic of personal knowledge graphs, development of PHKGs remains under-explored. A range of challenges surrounding the collection, linkage, and maintenance of personal health knowledge remains to be addressed to fully realize PHKGs.

Zhicheng Liang, Deborah L. McGuinness

Commonsense knowledge has proven to be beneficial to a variety of application areas, including question answering and natural language understanding. Previous work explored collecting commonsense knowledge triples automatically from text to increase the coverage of current commonsense knowledge graphs. We investigate a few machine learning approaches to mining commonsense knowledge triples using dictionary term definitions as inputs and provide some initial evaluation of the results. We start from extracting candidate triples using part-of-speech tag patterns from text, and then compare the performance of three existing models for triple scoring. Our experiments show that term definitions contain some valid and novel commonsense knowledge triples for some semantic relations, and also indicate some challenges with using existing triple scoring models.

Filip Ilievski, Alessandro Oltramari, Kaixin Ma et al.

Commonsense knowledge is essential for many AI applications, including those in natural language processing, visual processing, and planning. Consequently, many sources that include commonsense knowledge have been designed and constructed over the past decades. Recently, the focus has been on large text-based sources, which facilitate easier integration with neural (language) models and application to textual tasks, typically at the expense of the semantics of the sources and their harmonization. Efforts to consolidate commonsense knowledge have yielded partial success, with no clear path towards a comprehensive solution. We aim to organize these sources around a common set of dimensions of commonsense knowledge. We survey a wide range of popular commonsense sources with a special focus on their relations. We consolidate these relations into 13 knowledge dimensions. This consolidation allows us to unify the separate sources and to compute indications of their coverage, overlap, and gaps with respect to the knowledge dimensions. Moreover, we analyze the impact of each dimension on downstream reasoning tasks that require commonsense knowledge, observing that the temporal and desire/goal dimensions are very beneficial for reasoning on current downstream tasks, while distinctness and lexical knowledge have little impact. These results reveal preferences for some dimensions in current evaluation, and potential neglect of others.

Henrique Santos, Minor Gordon, Zhicheng Liang et al.

Commonsense question-answering (QA) tasks, in the form of benchmarks, are constantly being introduced for challenging and comparing commonsense QA systems. The benchmarks provide question sets that systems' developers can use to train and test new models before submitting their implementations to official leaderboards. Although these tasks are created to evaluate systems in identified dimensions (e.g. topic, reasoning type), this metadata is limited and largely presented in an unstructured format or completely not present. Because machine common sense is a fast-paced field, the problem of fully assessing current benchmarks and systems with regards to these evaluation dimensions is aggravated. We argue that the lack of a common vocabulary for aligning these approaches' metadata limits researchers in their efforts to understand systems' deficiencies and in making effective choices for future tasks. In this paper, we first discuss this MCS ecosystem in terms of its elements and their metadata. Then, we present how we are supporting the assessment of approaches by initially focusing on commonsense benchmarks. We describe our initial MCS Benchmark Ontology, an extensible common vocabulary that formalizes benchmark metadata, and showcase how it is supporting the development of a Benchmark tool that enables benchmark exploration and analysis.

Shruthi Chari, Oshani Seneviratne, Daniel M. Gruen et al.

Explainability has been a goal for Artificial Intelligence (AI) systems since their conception, with the need for explainability growing as more complex AI models are increasingly used in critical, high-stakes settings such as healthcare. Explanations have often added to an AI system in a non-principled, post-hoc manner. With greater adoption of these systems and emphasis on user-centric explainability, there is a need for a structured representation that treats explainability as a primary consideration, mapping end user needs to specific explanation types and the system's AI capabilities. We design an explanation ontology to model both the role of explanations, accounting for the system and user attributes in the process, and the range of different literature-derived explanation types. We indicate how the ontology can support user requirements for explanations in the domain of healthcare. We evaluate our ontology with a set of competency questions geared towards a system designer who might use our ontology to decide which explanation types to include, given a combination of users' needs and a system's capabilities, both in system design settings and in real-time operations. Through the use of this ontology, system designers will be able to make informed choices on which explanations AI systems can and should provide.

Shruthi Chari, Oshani Seneviratne, Daniel M. Gruen et al.

We addressed the problem of a lack of semantic representation for user-centric explanations and different explanation types in our Explanation Ontology (https://purl.org/heals/eo). Such a representation is increasingly necessary as explainability has become an important problem in Artificial Intelligence with the emergence of complex methods and an uptake in high-precision and user-facing settings. In this submission, we provide step-by-step guidance for system designers to utilize our ontology, introduced in our resource track paper, to plan and model for explanations during the design of their Artificial Intelligence systems. We also provide a detailed example with our utilization of this guidance in a clinical setting.

Shruthi Chari, Daniel M. Gruen, Oshani Seneviratne et al.

Interest in the field of Explainable Artificial Intelligence has been growing for decades and has accelerated recently. As Artificial Intelligence models have become more complex, and often more opaque, with the incorporation of complex machine learning techniques, explainability has become more critical. Recently, researchers have been investigating and tackling explainability with a user-centric focus, looking for explanations to consider trustworthiness, comprehensibility, explicit provenance, and context-awareness. In this chapter, we leverage our survey of explanation literature in Artificial Intelligence and closely related fields and use these past efforts to generate a set of explanation types that we feel reflect the expanded needs of explanation for today's artificial intelligence applications. We define each type and provide an example question that would motivate the need for this style of explanation. We believe this set of explanation types will help future system designers in their generation and prioritization of requirements and further help generate explanations that are better aligned to users' and situational needs.

Shruthi Chari, Daniel M. Gruen, Oshani Seneviratne et al.

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.

Shruthi Chari, Miao Qi, Nkcheniyere N. Agu et al.

Treatment recommendations within Clinical Practice Guidelines (CPGs) are largely based on findings from clinical trials and case studies, referred to here as research studies, that are often based on highly selective clinical populations, referred to here as study cohorts. When medical practitioners apply CPG recommendations, they need to understand how well their patient population matches the characteristics of those in the study cohort, and thus are confronted with the challenges of locating the study cohort information and making an analytic comparison. To address these challenges, we develop an ontology-enabled prototype system, which exposes the population descriptions in research studies in a declarative manner, with the ultimate goal of allowing medical practitioners to better understand the applicability and generalizability of treatment recommendations. We build a Study Cohort Ontology (SCO) to encode the vocabulary of study population descriptions, that are often reported in the first table in the published work, thus they are often referred to as Table 1. We leverage the well-used Semanticscience Integrated Ontology (SIO) for defining property associations between classes. Further, we model the key components of Table 1s, i.e., collections of study subjects, subject characteristics, and statistical measures in RDF knowledge graphs. We design scenarios for medical practitioners to perform population analysis, and generate cohort similarity visualizations to determine the applicability of a study population to the clinical population of interest. Our semantic approach to make study populations visible, by standardized representations of Table 1s, allows users to quickly derive clinically relevant inferences about study populations.

Alexander New, Sabbir M. Rashid, John S. Erickson et al.

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.

Oshani Seneviratne, Sabbir M. Rashid, Shruthi Chari et al.

With the rapid advancements in cancer research, the information that is useful for characterizing disease, staging tumors, and creating treatment and survivorship plans has been changing at a pace that creates challenges when physicians try to remain current. One example involves increasing usage of biomarkers when characterizing the pathologic prognostic stage of a breast tumor. We present our semantic technology approach to support cancer characterization and demonstrate it in our end-to-end prototype system that collects the newest breast cancer staging criteria from authoritative oncology manuals to construct an ontology for breast cancer. Using a tool we developed that utilizes this ontology, physician-facing applications can be used to quickly stage a new patient to support identifying risks, treatment options, and monitoring plans based on authoritative and best practice guidelines. Physicians can also re-stage existing patients or patient populations, allowing them to find patients whose stage has changed in a given patient cohort. As new guidelines emerge, using our proposed mechanism, which is grounded by semantic technologies for ingesting new data from staging manuals, we have created an enriched cancer staging ontology that integrates relevant data from several sources with very little human intervention.

Yue Liu, Tongtao Zhang, Zhicheng Liang et al.

We present an end-to-end approach that takes unstructured textual input and generates structured output compliant with a given vocabulary. Inspired by recent successes in neural machine translation, we treat the triples within a given knowledge graph as an independent graph language and propose an encoder-decoder framework with an attention mechanism that leverages knowledge graph embeddings. Our model learns the mapping from natural language text to triple representation in the form of subject-predicate-object using the selected knowledge graph vocabulary. Experiments on three different data sets show that we achieve competitive F1-Measures over the baselines using our simple yet effective approach. A demo video is included.

Yue Liu, Tao Ge, Kusum S. Mathews et al.

In the medical domain, identifying and expanding abbreviations in clinical texts is a vital task for both better human and machine understanding. It is a challenging task because many abbreviations are ambiguous especially for intensive care medicine texts, in which phrase abbreviations are frequently used. Besides the fact that there is no universal dictionary of clinical abbreviations and no universal rules for abbreviation writing, such texts are difficult to acquire, expensive to annotate and even sometimes, confusing to domain experts. This paper proposes a novel and effective approach - exploiting task-oriented resources to learn word embeddings for expanding abbreviations in clinical notes. We achieved 82.27% accuracy, close to expert human performance.

Henrique Santos, Victor Dantas, Vasco Furtado et al.

In the context of Smart Cities, indicator definitions have been used to calculate values that enable the comparison among different cities. The calculation of an indicator values has challenges as the calculation may need to combine some aspects of quality while addressing different levels of abstraction. Knowledge graphs (KGs) have been used successfully to support flexible representation, which can support improved understanding and data analysis in similar settings. This paper presents an operational description for a city KG, an indicator ontology that support indicator discovery and data visualization and an application capable of performing metadata analysis to automatically build and display dashboards according to discovered indicators. We describe our implementation in an urban mobility setting.

Paulo Pinheiro, Deborah L. McGuinness, Henrique Santos

Significant efforts have been made to understand and document knowledge related to scientific measurements. Many of those efforts resulted in one or more high-quality ontologies that describe some aspects of scientific measurements, but not in a comprehensive and coherently integrated manner. For instance, we note that many of these high-quality ontologies are not properly aligned, and more challenging, that they have different and often conflicting concepts and approaches for encoding knowledge about empirical measurements. As a result of this lack of an integrated view, it is often challenging for scientists to determine whether any two scientific measurements were taken in semantically compatible manners, thus making it difficult to decide whether measurements should be analyzed in combination or not. In this paper, we present the Human-Aware Sensor Network Ontology that is a comprehensive alignment and integration of a sensing infrastructure ontology and a provenance ontology. HASNetO has been under development for more than one year, and has been reviewed, shared and used by multiple scientific communities. The ontology has been in use to support the data management of a number of large-scale ecological monitoring activities (observations) and empirical experiments.

Henrique Santos, Vasco Furtado, Paulo Pinheiro et al.

As part of Smart Cities initiatives, national, regional and local governments all over the globe are under the mandate of being more open regarding how they share their data. Under this mandate, many of these governments are publishing data under the umbrella of open government data, which includes measurement data from city-wide sensor networks. Furthermore, many of these data are published in so-called data portals as documents that may be spreadsheets, comma-separated value (CSV) data files, or plain documents in PDF or Word documents. The sharing of these documents may be a convenient way for the data provider to convey and publish data but it is not the ideal way for data consumers to reuse the data. For example, the problems of reusing the data may range from difficulty opening a document that is provided in any format that is not plain text, to the actual problem of understanding the meaning of each piece of knowledge inside of the document. Our proposal tackles those challenges by identifying metadata that has been regarded to be relevant for measurement data and providing a schema for this metadata. We further leverage the Human-Aware Sensor Network Ontology (HASNetO) to build an architecture for data collected in urban environments. We discuss the use of HASNetO and the supporting infrastructure to manage both data and metadata in support of the City of Fortaleza, a large metropolitan area in Brazil.