We consider the problem of modifying a description logic concept in light of models represented as pointed interpretations. We call this setting model change, and distinguish three main kinds of changes: eviction, which consists of only removing models; reception, which incorporates models; and revision, which combines removal with incorporation of models in a single operation. We introduce a formal notion of revision and argue that it does not reduce to a simple combination of eviction and reception, contrary to intuition. We provide positive and negative results on the compatibility of eviction and reception for EL-bottom and ALC description logic concepts and on the compatibility of revision for ALC concepts.

Knowledge base (KB) embeddings aim at combining the capability of classical knowledge graph embeddings to generalize the information present in facts, the ABox, with conceptual knowledge represented in an ontology language, the TBox. Several authors have recently explored the idea of mapping concepts to convex regions in a vector space. This is useful to represent hierarchies, typically present in TBoxes, since more general concepts can be mapped to larger regions, containing those regions associated with more specific concepts. However, the power of convexity is rarely leveraged during the actual learning tasks. Here, we introduce BoxLitE, a KB embedding model for DL-Lite that allows for convex optimization. We show that for any satisfiable DL-Lite KB, there is a BoxLitE embedding that is a weakly faithful model. As a proof of concept, we show how to formulate the KB embedding task as a convex optimization problem and how to obtain embeddings with such desirable faithfulness property.

Decision trees are a popular machine learning method, valued for their inherent explainability. In Explainable AI, decision trees serve as surrogate models for complex black box AI models or as approximations of parts of such models. A key challenge of this approach is assessing how accurately the extracted decision tree represents the original model and determining the extent to which it can be trusted as an approximation of its behaviour. In this work, we investigate the use of the Probably Approximately Correct (PAC) framework to provide a theoretical guarantee of fidelity for decision trees extracted from AI models. Leveraging the theoretical foundations of the PAC framework, we adapt a decision tree algorithm to ensure a PAC guarantee under specific conditions. We focus on binary classification and conduct experiments where we extract decision trees from BERT-based language models with PAC guarantees. Our results indicate occupational gender bias in these models, which confirm previous results in the literature. Additionally, the decision tree format enhances the visualization of which occupations are most impacted by social bias.

In active learning, a learner attempts to learn from a teacher by posing questions. The questions made by the learner are called membership queries and are answered with ‘yes’ or ‘no’. This kind of query is often studied as part of a communication protocol that also includes equivalence queries. Intuitively, equivalence queries ask whether the idea of the learner about the knowledge of the teacher is correct or not. If not, then the teacher should provide a counterexample showing the difference. Here, we consider the teacher as a large language model (LLM) and study the case in which knowledge is expressed as an EL terminology. Membership queries ask whether concept inclusions are true or not. E.g., “Can algae be considered a subcategory of plant?”. Equivalence queries are simulated by a sample with concept inclusions labelled as positive or negative. We present a non-trivial extension of the ExactLearner tool to extract EL terminologies from LLMs. Given the relevant symbols as input (e.g., algae, plant, etc.), the tool tries to find how these symbols should be logically connected by posing questions to LLMs. To evaluate the approach, we present performance results of the ExactLearner in the task of reconstructing existing EL terminologies.

In group decisions or deliberations, stakeholders are often confronted with conflicting opinions. We investigate a logic-based way of expressing such opinions and a formal general notion of a middle ground between stakeholders. Inspired by the literature on preferences with hierarchical and lexicographic models, we instantiate our general framework to the case where stakeholders express their opinions using preference statements of the form ‘I prefer ‘a’ to ‘b’’, where ‘a’ and ‘b’ are alternatives expressed over some attributes, e.g., in a trolley problem, one can express I prefer to save 1 adult and 1 child to 2 adults (and 0 children). We prove theoretical results on the existence and uniqueness of middle grounds. In particular, we show that, for preference statements, middle grounds may not exist and may not be unique. We provide algorithms for deciding the existence and finding middle grounds.

We consider the exact and probably approximately correct (PAC) learning frameworks from computational learning theory and discuss opportunities and challenges for applying notions developed within these frameworks to extract information from black-box machine learning models, in particular, from language models. We discuss recent works that consider algorithms designed for the exact and PAC frameworks to extract information in the format of automata, Horn theories, and ontologies from machine learning models and possible applications of these approaches for understanding the models, studying biases, and knowledge acquisition.

Research on knowledge graph embeddings has recently evolved into knowledge base embeddings, where the goal is not only to map facts into vector spaces but also constrain the models so that they take into account the relevant conceptual knowledge available. This paper examines recent methods that have been proposed to embed knowledge bases in description logic into vector spaces through the lens of their geometric-based semantics. We identify several relevant theoretical properties, which we draw from the literature and sometimes generalize or unify. We then investigate how concrete embedding methods fit in this theoretical framework.

Abstract Smart devices that operate in a shared environment with people need to be aligned with their values and requirements. We study the problem of multiple stakeholders informing the same device on what the right thing to do is. Specifically, we focus on how to reach a middle ground among the stakeholders inevitably incoherent judgments on what the rules of conduct for the device should be. We formally define a notion of middle ground and discuss the main properties of this notion. Then, we identify three sufficient conditions on the class of Horn expressions for which middle grounds are guaranteed to exist. We provide a polynomial time algorithm that computes middle grounds, under these conditions. We also show that if any of the three conditions is removed then middle grounds for the resulting (larger) class may not exist. Finally, we implement our algorithm and perform experiments using data from the Moral Machine Experiment. We present conflicting rules for different countries and how the algorithm finds the middle ground in this case.

We present an approach for systematically probing a trained neural network to extract a symbolic abstraction of it, represented as a Boolean formula. We formulate this task within Angluin's exact learning framework, where a learner attempts to extract information from an oracle (in our work, the neural network) by posing membership and equivalence queries. We adapt Angluin's algorithm for Horn formula to the case where the examples are labelled w.r.t. an arbitrary Boolean formula in CNF (rather than a Horn formula). In this setting, the goal is to learn the smallest representation of all the Horn clauses implied by a Boolean formula—called its Horn envelope—which in our case correspond to the rules obeyed by the network. Our algorithm terminates in exponential time in the worst case and in polynomial time if the target Boolean formula can be closely approximated by its envelope. We also show that extracting Horn envelopes in polynomial time is as hard as learning CNFs in polynomial time. To showcase the applicability of the approach, we perform experiments on BERT based language models and extract Horn envelopes that expose occupation-based gender biases.

Formalisms based on temporal logics interpreted over finite strict linear orders, known in the literature as finite traces , have been used for temporal specification in automated planning, process modelling, (runtime) verification and synthesis of programs, as well as in knowledge representation and reasoning. In this article, we focus on first-order temporal logic on finite traces . We first investigate preservation of equivalences and satisfiability of formulas between finite and infinite traces, by providing a set of semantic and syntactic conditions to guarantee when the distinction between reasoning in the two cases can be blurred. Moreover, we show that the satisfiability problem on finite traces for several decidable fragments of first-order temporal logic is ExpSpace -complete, as in the infinite trace case, while it decreases to NExpTime when finite traces bounded in the number of instants are considered. This leads also to new complexity results for temporal description logics over finite traces. Finally, we investigate applications to planning and verification, in particular by establishing connections with the notions of insensitivity to infiniteness and safety from the literature.

We propose a new paradigm for Belief Change in which the new information is represented as sets of models, while the agent's body of knowledge is represented as a finite set of formulae, that is, a finite base. The focus on finiteness is crucial when we consider limited agents and reasoning algorithms. Moreover, having the input as arbitrary set of models is more general than the usual treatment of formulas as input. In this setting, we define new Belief Change operations akin to traditional expansion and contraction, and we identify the rationality postulates that emerge due to the finite representability requirement. We also analyse different logics concerning compatibility with our framework.

In Formal Concept Analysis, a base for a finite structure is a set of implications that characterizes all valid implications of the structure. This notion can be adapted to the context of Description Logic, where the base consists of a set of concept inclusions instead of implications. In this setting, concept expressions can be arbitrarily large. Thus, it is not clear whether a finite base exists and, if so, how large concept expressions may need to be. We first revisit results in the literature for mining ℰℒ⊥ bases from finite interpretations. Those mainly focus on finding a finite base or on fixing the role depth but potentially losing some of the valid concept inclusions with higher role depth. We then present a new strategy for mining ℰℒ⊥ bases which is adaptable in the sense that it can bound the role depth of concepts depending on the local structure of the interpretation. Our strategy guarantees to capture all ℰℒ⊥ concept inclusions holding in the interpretation, not only the ones up to a fixed role depth. We also consider the case of confident ℰℒ⊥ bases, which requires that some proportion of the domain of the interpretation satisfies the base, instead of the whole domain. This case is useful to cope with noisy data.

The Craig interpolation property (CIP) states that an interpolant for an implication exists iff it is valid. The projective Beth definability property (PBDP) states that an explicit definition exists iff a formula stating implicit definability is valid. Thus, the CIP and PBDP reduce potentially hard existence problems to entailment in the underlying logic. Description (and modal) logics with nominals and/or role inclusions do not enjoy the CIP nor the PBDP, but interpolants and explicit definitions have many applications, in particular in concept learning, ontology engineering, and ontology-based data management. In this article, we show that, even without Beth and Craig, the existence of interpolants and explicit definitions is decidable in description logics with nominals and/or role inclusions such as 𝒜ℒ𝒞𝒪, 𝒜ℒ𝒞ℋ, and 𝒜ℒ𝒞ℋ𝒪ℐ and corresponding hybrid modal logics. However, living without Beth and Craig makes these problems harder than entailment: the existence problems become 2ExpTime -complete in the presence of an ontology or the universal modality, and coNExpTime -complete otherwise. We also analyze explicit definition existence if all symbols (except the one that is defined) are admitted in the definition. In this case, the complexity depends on whether one considers individual or concept names. Finally, we consider the problem of computing interpolants and explicit definitions if they exist and turn the complexity upper bound proof into an algorithm computing them, at least for description logics with role inclusions.

In Formal Concept Analysis, a base for a finite structure is a set of implications that characterizes all valid implications of the structure. This notion can be adapted to the context of Description Logic, where the base consists of a set of concept inclusions instead of implications. In this setting, concept expressions can be arbitrarily large. Thus, it is not clear whether a finite base exists and, if so, how large concept expressions may need to be. We first revisit results in the literature for mining EL bases from finite interpretations. Those mainly focus on finding a finite base or on fixing the role depth but potentially losing some of the valid concept inclusions with higher role depth. We then present a new strategy for mining EL bases which is adaptable in the sense that it can bound the role depth of concepts depending on the local structure of the interpretation. Our strategy guarantees to capture all EL concept inclusions holding in the interpretation, not only the ones up to a fixed role depth.

The Craig interpolation property (CIP) states that an interpolant for an implication exists iff it is valid. The projective Beth definability property (PBDP) states that an explicit definition exists iff a formula stating implicit definability is valid. Thus, the CIP and PBDP transform potentially hard existence problems into deduction problems in the underlying logic. Description Logics with nominals and/or role inclusions do not enjoy the CIP nor PBDP, but interpolants and explicit definitions have many potential applications in ontology engineering and ontology-based data management. In this article we show the following: even without Craig and Beth, the existence of interpolants and explicit definitions is decidable in description logics with nominals and/or role inclusions such as ALCO, ALCH and ALCHIO. However, living without Craig and Beth makes this problem harder than deduction: we prove that the existence problems become 2EXPTIME-complete, thus one exponential harder than validity. The existence of explicit definitions is 2EXPTIME-hard even if one asks for a definition of a nominal using any symbol distinct from that nominal, but it becomes EXPTIME-complete if one asks for a definition of a concept name using any symbol distinct from that concept name.

Definite descriptions are phrases of the form ‘the x such that φ’, used to refer to single entities in a context. They are often more meaningful to users than individual names alone, in particular when modelling or querying data over ontologies. We investigate free description logics with both individual names and definite descriptions as terms of the language, while also accounting for their possible lack of denotation. We focus on the extensions of ALC and, respectively, EL with nominals, the universal role, and definite descriptions. We show that standard reasoning in these extensions is not harder than in the original languages, and we characterise the expressive power of concepts relative to first-order formulas using a suitable notion of bisimulation. Moreover, we lay the foundations for automated support for definite descriptions generation by studying the complexity of deciding the existence of definite descriptions for an individual under an ontology. Finally, we provide a polynomial-time reduction of reasoning in other free description logic languages based on dual-domain semantics to the case of partial interpretations.

We investigate the complexity of learning query inseparable εℒℋ ontologies in a variant of Angluin's exact learning model. Given a fixed data instance A* and a query language

We address the problem of handling provenance information in ELHr ontologies. We consider a setting recently introduced for ontology-based data access, based on semirings and extending classical data provenance, in which ontology axioms are annotated with provenance tokens. A consequence inherits the provenance of the axioms involved in deriving it, yielding a provenance polynomial as an annotation. We analyse the semantics for the ELHr case and show that the presence of conjunctions poses various difficulties for handling provenance, some of which are mitigated by assuming multiplicative idempotency of the semiring. Under this assumption, we study three problems: ontology completion with provenance, computing the set of relevant axioms for a consequence, and query answering.

We investigate learnability of possibilistic theories from entailments in light of Angluin’s exact learning model. We consider cases in which only membership, only equivalence, and both kinds of queries can be posed by the learner. We then show that, for a large class of problems, polynomial time learnability results for classical logic can be transferred to the respective possibilistic extension. In particular, it follows from our results that the possibilistic extension of propositional Horn theories is exactly learnable in polynomial time. As polynomial time learnability in the exact model is transferable to the classical probably approximately correct (PAC) model extended with membership queries, our work also establishes such results in this model.

Abstract We study translations from metric temporal logic (MTL) over the natural numbers to linear temporal logic (LTL). In particular, we present two approaches for translating from MTL to LTL which preserve the complexity of the satisfiability problem for MTL. In each of these approaches we consider the case where the mapping between states and time points is given by (i) a strict monotonic function and by (ii) a non-strict monotonic function (which allows multiple states to be mapped to the same time point). We use this logic to model examples from robotics, traffic management, and scheduling, discussing the effects of different modelling choices. Our translations allow us to utilise LTL solvers to solve satisfiability and we empirically compare the translations, showing in which cases one performs better than the other. We also define a branching-time version of the logic and provide translations into computation tree logic.

In contrast to qualitative linear temporal logics, which can be used to state that some property will eventually be satisfied, metric temporal logics allow us to formulate constraints on how long it may take until the property is satisfied. While most of the work on combining description logics (DLs) with temporal logics has concentrated on qualitative temporal logics, there is a growing interest in extending this work to the quantitative case. In this article, we complement existing results on the combination of DLs with metric temporal logics by introducing interval-rigid concept and role names. Elements included in an interval-rigid concept or role name are required to stay in it for some specified amount of time. We investigate several combinations of (metric) temporal logics with A ℒ C by either allowing temporal operators only on the level of axioms or also applying them to concepts. In contrast to most existing work on the topic, we consider a timeline based on the integers and also allow assertional axioms. We show that the worst-case complexity does not increase beyond the previously known bound of 2-E xp S pace and investigate in detail how this complexity can be reduced by restricting the temporal logic and the occurrences of interval-rigid names.

Attributed description logic is a recently proposed formalism, targeted for graph-based representation formats, which enriches description logic concepts and roles with finite sets of attribute-value pairs, called annotations. One of the most important uses of annotations is to record provenance information. In this work, we first investigate the complexity of satisfiability and query answering for attributed DL-LiteR ontologies. We then propose a new semantics, based on provenance semirings, for integrating provenance information with query answering. Finally, we establish complexity results for satisfiability and query answering under this semantics.

Linear temporal logic over finite traces is used as a formalism for temporal specification in automated planning, process modelling and (runtime) verification. In this paper, we investigate first-order temporal logic over finite traces, lifting some known results to a more expressive setting. Satisfiability in the two-variable monodic fragment is shown to be EXPSPACE-complete, as for the infinite trace case, while it decreases to NEXPTIME when we consider finite traces bounded in the number of instants. This leads to new complexity results for temporal description logics over finite traces. We further investigate satisfiability and equivalences of formulas under a model-theoretic perspective, providing a set of semantic conditions that characterise when the distinction between reasoning over finite and infinite traces can be blurred. Finally, we apply these conditions to planning and verification.

Ontology-based data access (OBDA) is a popular paradigm for querying heterogeneous data sources by connecting them through mappings to an ontology. In OBDA, it is often difficult to reconstruct why a tuple occurs in the answer of a query. We address this challenge by enriching OBDA with provenance semirings, taking inspiration from database theory. In particular, we investigate the problems of (i) deciding whether a provenance annotated OBDA instance entails a provenance annotated conjunctive query, and (ii) computing a polynomial representing the provenance of a query entailed by a provenance annotated OBDA instance. Differently from pure databases, in our case, these polynomials may be infinite. To regain finiteness, we consider idempotent semirings, and study the complexity in the case of DL-LiteR ontologies. We implement Task (ii) in a state-of-the-art OBDA system and show the practical feasibility of the approach through an extensive evaluation against two popular benchmarks.

Conjunctive query answering over databases with constraints – also known as (tuple-generating) dependencies – is considered a central database task. To this end, several versions of a construction called chase have been described. Given a set Sigma of dependencies, it is interesting to ask which constraints not contained in Sigma that are initially satisfied in a given database instance are preserved when computing a chase over Sigma. Such constraints are an example for the more general class of incidental constraints, which when added to Sigma as new dependencies do not affect certain answers and might even speed up query answering. After formally introducing incidental constraints, we show that deciding incidentality is undecidable for tuple-generating dependencies, even in cases for which query entailment is decidable. For dependency sets with a finite universal model, the core chase can be used to decide incidentality. For the infinite case, we propose the stable chase, which generalises the core chase, and study its relation to incidental constraints.

In modelling real-world knowledge, there often arises a need to represent and reason with meta-knowledge. To equip description logics (DLs) for dealing with such ontologies, we enrich DL concepts and roles with finite sets of attribute–value pairs, called annotations, and allow concept inclusions to express constraints on annotations. We investigate a range of DLs starting from the lightweight description logic EL, covering the prototypical ALCH, and extending to the very expressive SROIQ, the DL underlying OWL 2 DL.

We investigate the problem of learning description logic (DL) ontologies in Angluin et al.’s framework of exact learning via queries posed to an oracle. We consider membership queries of the form “is a tuple a of individuals a certain answer to a data retrieval query q in a given ABox and the unknown target ontology?” and completeness queries of the form “does a hypothesis ontology entail the unknown target ontology?” Given a DL L and a data retrieval query language Q, we study polynomial learnability of ontologies in L using data retrieval queries in Q and provide an almost complete classification for DLs that are fragments of EL with role inclusions and of DL-Lite and for data retrieval queries that range from atomic queries and EL/ELI-instance queries to conjunctive queries. Some results are proved by non-trivial reductions to learning from subsumption examples.

We introduce metric temporal description logics (mTDLs) as combinations of the classical description logic ALC with (a) LTLbin, an extension of the temporal logic LTL with succinctly represented intervals, and (b) metric temporal logic MTL, extending LTLbinwith capabilities to quantitatively reason about time delays. Our main contributions are algorithms and tight complexity bounds for the satisfiability problem in these mTDLs: For mTDLs based on (fragments of) LTLbin, we establish complexity bounds ranging from EXPTIME to 2EXPSPACE. For mTDLs based on (fragments of) MTL interpreted over the naturals, we establish complexity bounds ranging from EXPSPACE to 2EXPSPACE.