Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets

Visual Question Answering (VQA) is the task of answering a question about an image and requires processing multimodal input and reasoning to obtain the answer. Modular solutions that use declarative representations within the reasoning component have a clear advantage over end-to-end trained systems regarding interpretability. The downside is that crafting the rules for such a component can be an additional burden on the developer. We address this challenge by presenting an approach for declarative knowledge distillation from Large Language Models (LLMs). Our method is to prompt an LLM to extend an initial theory on VQA reasoning, given as an answer-set program, to meet the requirements of the VQA task. Examples from the VQA dataset are used to guide the LLM, validate the results, and mend rules if they are not correct by using feedback from the ASP solver. We demonstrate that our approach works on the prominent CLEVR and GQA datasets. Our results confirm that distilling knowledge from LLMs is in fact a promising direction besides data-driven rule learning approaches.

Deontic Paradoxes in ASP with Weak Constraints

The rise of powerful AI technology for a range of applications that are sensitive to legal, social, and ethical norms demands decision-making support in presence of norms and regulations. Normative reasoning is the realm of deontic logics, that are challenged by well-known benchmark problems (deontic paradoxes), and lack efficient computational tools. In this paper, we use Answer Set Programming (ASP) for addressing these shortcomings and showcase how to encode and resolve several well-known deontic paradoxes utilizing weak constraints. By abstracting and generalizing this encoding, we present a methodology for translating normative systems in ASP with weak constraints. This methodology is applied to "ethical" versions of Pac-man, where we obtain a comparable performance with related works, but ethically preferable results.

Contextual Reasoning for Scene Generation (Technical Report)

We present a continuation to our previous work, in which we developed the MR-CKR framework to reason with knowledge overriding across contexts organized in multi-relational hierarchies. Reasoning is realized via ASP with algebraic measures, allowing for flexible definitions of preferences. In this paper, we show how to apply our theoretical work to real autonomous-vehicle scene data. Goal of this work is to apply MR-CKR to the problem of generating challenging scenes for autonomous vehicle learning. In practice, most of the scene data for AV learning models common situations, thus it might be difficult to capture cases where a particular situation occurs (e.g. partial occlusions of a crossing pedestrian). The MR-CKR model allows for data organization exploiting the multi-dimensionality of such data (e.g., temporal and spatial). Reasoning over multiple contexts enables the verification and configuration of scenes, using the combination of different scene ontologies. We describe a framework for semantically guided data generation, based on a combination of MR-CKR and Algebraic Measures. The framework is implemented in a proof-of-concept prototype exemplifying some cases of scene generation.

Answer-Set Programming for Lexicographical Makespan Optimisation in Parallel Machine Scheduling

We deal with a challenging scheduling problem on parallel machines with sequence-dependent setup times and release dates from a real-world application of semiconductor work-shop production. There, jobs can only be processed by dedicated machines, thus few machines can determine the makespan almost regardless of how jobs are scheduled on the remaining ones. This causes problems when machines fail and jobs need to be rescheduled. Instead of optimising only the makespan, we put the individual machine spans in non-ascending order and lexicographically minimise the resulting tuples. This achieves that all machines complete as early as possible and increases the robustness of the schedule. We study the application of Answer-Set Programming (ASP) to solve this problem. While ASP eases modelling, the combination of timing constraints and the considered objective function challenges current solving technology. The former issue is addressed by using an extension of ASP by difference logic. For the latter, we devise different algorithms that use multi-shot solving. To tackle industrial-sized instances, we study different approximations and heuristics. Our experimental results show that ASP is indeed a promising KRR paradigm for this problem and is competitive with state-of-the-art CP and MIP solvers. Under consideration in Theory and Practice of Logic Programming (TPLP).

A Neuro-Symbolic ASP Pipeline for Visual Question Answering

We present a neuro-symbolic visual question answering (VQA) pipeline for CLEVR, which is a well-known dataset that consists of pictures showing scenes with objects and questions related to them. Our pipeline covers (i) training neural networks for object classification and bounding-box prediction of the CLEVR scenes, (ii) statistical analysis on the distribution of prediction values of the neural networks to determine a threshold for high-confidence predictions, and (iii) a translation of CLEVR questions and network predictions that pass confidence thresholds into logic programs so that we can compute the answers using an ASP solver. By exploiting choice rules, we consider deterministic and non-deterministic scene encodings. Our experiments show that the non-deterministic scene encoding achieves good results even if the neural networks are trained rather poorly in comparison with the deterministic approach. This is important for building robust VQA systems if network predictions are less-than perfect. Furthermore, we show that restricting non-determinism to reasonable choices allows for more efficient implementations in comparison with related neuro-symbolic approaches without loosing much accuracy. This work is under consideration for acceptance in TPLP.

Chasing Streams with Existential Rules

We study reasoning with existential rules to perform query answering over streams of data. On static databases, this problem has been widely studied, but its extension to rapidly changing data has not yet been considered. To bridge this gap, we extend LARS, a well-known framework for rule-based stream reasoning, to support existential rules. For that, we show how to translate LARS with existentials into a semantics-preserving set of existential rules. As query answering with such rules is undecidable in general, we describe how to leverage the temporal nature of streams and present suitable notions of acyclicity that ensure decidability.

CQELS 2.0: Towards A Unified Framework for Semantic Stream Fusion

We present CQELS 2.0, the second version of Continuous Query Evaluation over Linked Streams. CQELS 2.0 is a platform-agnostic federated execution framework towards semantic stream fusion. In this version, we introduce a novel neural-symbolic stream reasoning component that enables specifying deep neural network (DNN) based data fusion pipelines via logic rules with learnable probabilistic degrees as weights. As a platform-agnostic framework, CQELS 2.0 can be implemented for devices with different hardware architectures (from embedded devices to cloud infrastructures). Moreover, this version also includes an adaptive federator that allows CQELS instances on different nodes in a network to coordinate their resources to distribute processing pipelines by delegating partial workloads to their peers via subscribing continuous queries

Reasoning on Multi-Relational Contextual Hierarchies via Answer Set Programming with Algebraic Measures

Dealing with context dependent knowledge has led to different formalizations of the notion of context. Among them is the Contextualized Knowledge Repository (CKR) framework, which is rooted in description logics but links on the reasoning side strongly to logic programs and Answer Set Programming (ASP) in particular. The CKR framework caters for reasoning with defeasible axioms and exceptions in contexts, which was extended to knowledge inheritance across contexts in a coverage (specificity) hierarchy. However, the approach supports only this single type of contextual relation and the reasoning procedures work only for restricted hierarchies, due to non-trivial issues with model preference under exceptions. In this paper, we overcome these limitations and present a generalization of CKR hierarchies to multiple contextual relations, along with their interpretation of defeasible axioms and preference. To support reasoning, we use ASP with algebraic measures, which is a recent extension of ASP with weighted formulas over semirings that allows one to associate quantities with interpretations depending on the truth values of propositional atoms. Notably, we show that for a relevant fragment of CKR hierarchies with multiple contextual relations, query answering can be realized with the popular asprin framework. The algebraic measures approach is more powerful and enables e.g. reasoning with epistemic queries over CKRs, which opens interesting perspectives for the use of quantitative ASP extensions in other applications. Under consideration for acceptance in Theory and Practice of Logic Programming (TPLP).

Reasoning on $\textit{DL-Lite}_{\cal R}$ with Defeasibility in ASP

Reasoning on defeasible knowledge is a topic of interest in the area of description logics, as it is related to the need of representing exceptional instances in knowledge bases. In this direction, in our previous works we presented a framework for representing (contextualized) OWL RL knowledge bases with a notion of justified exceptions on defeasible axioms: reasoning in such framework is realized by a translation into ASP programs. The resulting reasoning process for OWL RL, however, introduces a complex encoding in order to capture reasoning on the negative information needed for reasoning on exceptions. In this paper, we apply the justified exception approach to knowledge bases in $\textit{DL-Lite}_{\cal R}$, i.e., the language underlying OWL QL. We provide a definition for $\textit{DL-Lite}_{\cal R}$ knowledge bases with defeasible axioms and study their semantic and computational properties. In particular, we study the effects of exceptions over unnamed individuals. The limited form of $\textit{DL-Lite}_{\cal R}$ axioms allows us to formulate a simpler ASP encoding, where reasoning on negative information is managed by direct rules. The resulting materialization method gives rise to a complete reasoning procedure for instance checking in $\textit{DL-Lite}_{\cal R}$ with defeasible axioms. Under consideration in Theory and Practice of Logic Programming (TPLP).

Constraint Monotonicity, Epistemic Splitting and Foundedness Are Too Strong in Answer Set Programming

Recently, some researchers in the community of answer set programming introduced the notions of subjective constraint monotonicity, epistemic splitting, and foundedness for epistemic logic programs, aiming to use them as main criteria/intuitions to compare different answer set semantics proposed in the literature on how they comply with these intuitions. In this note we demonstrate that these three properties are too strong and may exclude some desired answer sets/world views. Therefore, such properties should not be used as necessary conditions for answer set semantics.