Ilaria Tiddi

Hybrid Intelligence (HI) studies how humans and AI systems collaborate by combining complementary capabilities in complex, context-dependent settings. Across applications, recurring structural features emerge: heterogeneous teams, capability-dependent tasks, assigned roles, and contextual influences on behaviour and outcomes. Together, these properties show that HI systems function as coordinated socio-technical units—organised teams in which human and artificial agents depend on each other’s capabilities to achieve shared goals. However, most existing accounts remain conceptual and rarely specify how these elements are formally related. As a result, HI systems are difficult to analyse systematically, compare across domains, or reuse through shared artefacts. We address this gap by proposing a semantic model that makes the structural organisation of Human–AI collaboration explicit. Drawing on prior work and seven representative use cases, we derive the representational and reasoning requirements implied by HI and translate them into explicit information needs guiding model construction. The resulting model—implemented as the Hybrid Intelligence Ontology and the Hybrid Intelligence Thesaurus (HINT)—formalises team composition, capability–task dependencies, contextual influences, and evaluation structures in machine-interpretable form, while reusing established Semantic Web standards to ensure interoperability. Validation through structural constraints, query-based testing, and application to a new use case demonstrates its adequacy.

Humans quickly learn new concepts from a small number of examples. Replicating this capacity with Artificial Intelligence (AI) systems has proven to be challenging. When it comes to learning subjective tasks-where there is an evident scarcity of data-this capacity needs to be recreated. In this work, we propose an intuitive human-agent teaching architecture in which the human can teach an agent how to perform a task by providing demonstrations, i.e., examples. To have an intuitive interaction, we argue that the agent should be able to learn incrementally from a few single examples. To allow for this, our objective is to broaden the agent's task understanding using domain knowledge. Then, using a learning method to enable the agent to learn efficiently from a limited number of examples. Finally, to optimize how human can select the most representative and less redundant examples to provide the agent with. We apply our proposed method to the subjective task of ingredient substitution, where the agent needs to learn how to substitute ingredients in recipes based on human examples. We replicate human input using the Recipe1MSubs dataset. In our experiments, the agent achieves half its task performance after only 100 examples are provided, compared to the complete training set of 50k examples. We show that by providing examples in strategic order along with a learning method that leverages external symbolic knowledge, the agent can generalize more efficiently.

Personal service robots are deployed to support daily living in domestic environments, particularly for elderly and individuals requiring assistance. These robots must perceive complex and dynamic surroundings, understand tasks, and execute context-appropriate actions. However, current systems rely on proprietary, hard-coded solutions tied to specific hardware and software, resulting in siloed implementations that are difficult to adapt and scale across platforms. Ontologies and Knowledge Graphs (KGs) offer a solution to enable interoperability across systems, through structured and standardized representations of knowledge and reasoning. However, symbolic systems such as KGs and ontologies struggle with raw and noisy sensory input. In contrast, multimodal language models are well suited for interpreting input such as images and natural language, but often lack transparency, consistency, and knowledge grounding. In this work, we propose a neurosymbolic framework that combines the perceptual strengths of multimodal language models with the structured representations provided by KGs and ontologies, with the aim of supporting interoperability in robotic applications. Our approach generates ontology-compliant KGs that can inform robot behavior in a platform-independent manner. We evaluated this framework by integrating robot perception data, ontologies, and five multimodal models (three LLaMA and two GPT models), using different modes of neural-symbolic interaction. We assess the consistency and effectiveness of the generated KGs across multiple runs and configurations, and perform statistical analyzes to evaluate performance. Results show that GPT-o1 and LLaMA 4 Maverick consistently outperform other models. However, our findings also indicate that newer models do not guarantee better results, highlighting the critical role of the integration strategy in generating ontology-compliant KGs.

We present an overview of AI-based tools assisting the research process, analyzing them from the point of view of Hybrid (human-AI) Intelligence (HI). While Autonomous Research Assistants (RAs) are gaining new interest by the latest advancements in AI (cf. Large Language Models), limitations arise when deployed in real-world use-cases. Starting from the hypothesis that principles from the emerging field of HI could enhance the synergy between researchers and AI tools, we explore what requirements allow to create HI RAs, using a survey of existing systems. We performed a review of 47 relevant articles published in the last 10 years, and we analyzed them according to various capabilities and characteristics proposed in the Hybrid Intelligence literature. Finally, we identify which future research lines could be followed to develop assistive systems that better combine the capabilities of humans and artificial RAs in a synergistic way.

Event-centric knowledge graphs help enhance coherence to otherwise fragmented and overwhelming data by establishing causal and temporal connections using relevant data. We address the challenge of automatically constructing event-centric knowledge graphs from generic ones. We present ChronoGrapher, a two-step system to build an event-centric knowledge graph from grand events such as the French Revolution. First, a pruned, semantically informed best-first search traversal retrieves a subgraph from large, open-domain knowledge graphs. We define event-centric filters to prune the search space and a heuristic ranking to prioritize nodes like events. Second, we combine a structured triple enrichment method with a text-based triple enrichment method to build event-centric knowledge graphs. ChronoGrapher demonstrates adaptability across datasets like DBpedia and Wikidata, outperforming approaches from the literature. Furthermore, it is designed to be flexible and to operate over any knowledge graph accessible through Header, Dictionary, and Triples dumps or SPARQL endpoints. To evaluate the utility of these constructed graphs, we conduct a preliminary user study comparing different prompting techniques for event-centric question-answering. Our results demonstrate that prompts enriched with event-centric knowledge graph triples yield more factual answers, measured by how well answers are grounded in source information, than those enriched with generic triples or base prompts, while preserving succinctness and relevance.

Shapley value-based explanations are widely utilized to demystify predictions made by opaque models. Approaches to estimating Shapley values often approximate explanation games as inessential and estimate the Shapley value directly as feature attribution with a limited capacity to quantify feature interactions. This paper introduces a new approach for calculating Shapley values that relaxes the assumption of inessential games and is proven to provide additive feature attribution. The initial formulation of the proposed approach includes the estimation of game values in their Möbius representation with exponentially many parameters, but we put forward a polynomial-time algorithm designed to manage the game's numerous values and achieve an efficient linear-time computation of the Shapley value. Moreover, this formulation uniquely enables identifying only the significant high-order feature interactions amidst a potentially exponential set. Through experiments, we demonstrate the robust performance of our methodology in game estimation and in providing explanations for multiple black-box models.