Johannes Oetsch

Thomas Eiter, Nelson Higuera Ruiz, Johannes Oetsch

Visual Question Answering (VQA) is the task of answering questions about images, requiring the integration of multimodal input and reasoning. Modular approaches that incorporate logic-based representations into the reasoning component offer clear advantages over end-to-end trained systems, particularly in terms of interpretability. However, adapting or extending these representations when task requirements change can place a significant burden on developers. To address this challenge, we present an approach for distilling rules from Large Language Models (LLMs). Our method prompts an LLM to extend an initial VQA reasoning theory, expressed as an answer-set program, to meet new requirements of the task. Examples from VQA datasets guide the LLM, validate the results, and help correct erroneous rules by leveraging feedback from the ASP solver. We demonstrate that our approach is effective across diverse VQA datasets. Notably, only a few examples are needed to elicit correct rules from LLMs. Our experiments suggest that rule distillation from LLMs is a promising alternative to traditional data-driven rule learning approaches. Under consideration in Theory and Practice of Logic Programming (TPLP).

Thomas Eiter, Nelson Higuera, Johannes Oetsch et al.

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.

Thomas Eiter, Tobias Geibinger, Nysret Musliu et al.

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).

Rafael Bankosegger, Thomas Eiter, Johannes Oetsch

Reinforcement Learning (RL) enables autonomous agents to learn policies from experience, but realistic problems often involve enormous state spaces, making learning and generalisation challenging. Abstraction and approximation are therefore essential. Relational Reinforcement Learning (RRL) offers a way to reason about objects and their relations, and the CARCASS framework by Martijn van Otterlo demonstrates how logical representations can model Markov Decision Processes (MDPs) in first-order domains. Originally implemented in Prolog, CARCASS leverages domain knowledge to create powerful abstractions. We explore Answer-Set Programming (ASP), which is a rich and, contrary to Prolog, fully declarative modelling language, to realise CARCASS abstractions. We evaluate our ASP-based implementation in case studies of two domains, viz. Blocks World and Minigrid. Our results indicate that CARCASS with ASP provides a promising approach to constructing abstractions for RL, especially when domain knowledge is available.

Thomas Eiter, Tobias Geibinger, Tobias Kaminski et al.

We present the solver asp-fzn for Constraint Answer Set Programming (CASP), which extends ASP with linear constraints. Our approach is based on translating CASP programs into the solver-independent FlatZinc language that supports several Constraint Programming and Integer Programming backend solvers. Our solver supports a rich language of linear constraints, including some common global constraints. As for evaluation, we show that asp-fzn is competitive with state-of-the-art ASP solvers on benchmarks taken from past ASP competitions. Furthermore, we evaluate it on several CASP problems from the literature and compare its performance with clingcon, which is a prominent CASP solver that supports most of the asp-fzn language. The performance of asp-fzn is very promising as it is already competitive on plain ASP and even outperforms clingcon on some CASP benchmarks.

Jakob Johannes Bauer, Thomas Eiter, Nelson Higuera Ruiz et al.

Visual Question Answering (VQA) is a challenging problem that requires to process multimodal input. Answer-Set Programming (ASP) has shown great potential in this regard to add interpretability and explainability to modular VQA architectures. In this work, we address the problem of how to integrate ASP with modules for vision and natural language processing to solve a new and demanding VQA variant that is concerned with images of graphs (not graphs in symbolic form). Images containing graph-based structures are an ubiquitous and popular form of visualisation. Here, we deal with the particular problem of graphs inspired by transit networks, and we introduce a novel dataset that amends an existing one by adding images of graphs that resemble metro lines. Our modular neuro-symbolic approach combines optical graph recognition for graph parsing, a pretrained optical character recognition neural network for parsing labels, Large Language Models (LLMs) for language processing, and ASP for reasoning. This method serves as a first baseline and achieves an overall average accuracy of 73% on the dataset. Our evaluation provides further evidence of the potential of modular neuro-symbolic systems, in particular with pretrained models that do not involve any further training and logic programming for reasoning, to solve complex VQA tasks.

Thomas Eiter, Jan Hadl, Nelson Higuera et al.

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.

Johannes Oetsch, Jörg Pührer, Hans Tompits

We introduce a stepping methodology for answer-set programming (ASP) that allows for debugging answer-set programs and is based on the stepwise application of rules. Similar to debugging in imperative languages, where the behaviour of a program is observed during a step-by-step execution, stepping for ASP allows for observing the effects that rule applications have in the computation of an answer set. While the approach is inspired from debugging in imperative programming, it is conceptually different to stepping in other paradigms due to non-determinism and declarativity that are inherent to ASP. In particular, unlike statements in an imperative program that are executed following a strict control flow, there is no predetermined order in which to consider rules in ASP during a computation. In our approach, the user is free to decide which rule to consider active in the next step following his or her intuition. This way, one can focus on interesting parts of the debugging search space. Bugs are detected during stepping by revealing differences between the actual semantics of the program and the expectations of the user. As a solid formal basis for stepping, we develop a framework of computations for answer-set programs. For fully supporting different solver languages, we build our framework on an abstract ASP language that is sufficiently general to capture different solver languages. To this end, we make use of abstract constraints as an established abstraction for popular language constructs such as aggregates. Stepping has been implemented in SeaLion, an integrated development environment for ASP. We illustrate stepping using an example scenario and discuss the stepping plugin of SeaLion. Moreover, we elaborate on methodological aspects and the embedding of stepping in the ASP development process.

Marina De Vos, Doğa Gizem Kıza, Johannes Oetsch et al.

While past research in answer-set programming (ASP) mainly focused on theory, ASP solver technology, and applications, the present work situates itself in the context of a quite recent research trend: development support for ASP. In particular, we propose to augment answer-set programs with additional meta-information formulated in a dedicated annotation language, called LANA. This language allows the grouping of rules into coherent blocks and to specify language signatures, types, pre- and postconditions, as well as unit tests for such blocks. While these annotations are invisible to an ASP solver, as they take the form of program comments, they can be interpreted by tools for documentation, testing, and verification purposes, as well as to eliminate sources of common programming errors by realising syntax checking or code completion features. To demonstrate its versatility, we introduce two such tools, viz. (i) ASPDOC, for generating an HTML documentation for a program based on the annotated information, and (ii) ASPUNIT, for running and monitoring unit tests on program blocks. LANA is also exploited in the SeaLion system, an integrated development environment for ASP based on Eclipse. To appear in Theory and Practice of Logic Programming