Thomas Eiter
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Thomas Eiter has a total of 222 co-authors. Here are the top co-authors by number of shared publications:
- Michael Fink
Institute of Information Systems, Vienna University of Technology, Vienna, Austria
22 shared publications - Luc De Raedt
KU Leuven
11 shared publications - Miroslaw Truszczynski
University of Kentucky
11 shared publications - Michael J. Maher
Reasoning Research Institute
10 shared publications - Chitta Baral
Arizona State University
9 shared publications - Gopal Gupta
University of Texas at Dallas
9 shared publications
Latest Publications
- Open Access
- 13 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computational Logic
- Vol. 27 (4) , 1-72
Refining Gelfond’s Rationality Principle: Towards More Comprehensive Foundational Principles for Answer Set Semantics
Non-monotonic logic programming is the basis for a declarative problem-solving paradigm known as answer set programming (ASP), where solutions to problems are encoded by intended models (answer sets) of a logic program. Departing from the seminal definition by Gelfond and Lifschitz for simple normal logic programs, various answer set semantics have been proposed for extensions such as disjunctive logic programs and epistemic logic programs. In the latter case, the semantics consists of sets of answer sets called world views. In general, it seems infeasible to formally prove whether a proposal defines answer sets/world views that correspond exactly to the solutions of any problem intuitively represented by a logic program. It is thus necessary to develop some general principles and use them as a baseline to intuitively compare and assess different answer set and world view semantics, respectively. Towards such a baseline, we consider two important questions: (1) Should the minimal model property, constraint monotonicity, and foundedness as defined in the literature be mandatory conditions for an answer set semantics in general? (2) If not, what other properties could be considered as alternative principles for answer set semantics? We address the two questions with several contributions. First, we use examples to demonstrate that requiring minimal models, constraint monotonicity, and foundedness as mandatory conditions may exclude expected answer sets for some simple disjunctive programs and world views for some epistemic specifications. Second, we evolve the Gelfond answer set (GAS) principles for answer set construction by refining Gelfond’s rationality principle to well-supportedness, minimality w.r.t. negation by default, and minimality w.r.t. epistemic negation. The principle of well-supportedness guarantees that every answer set is constructible from if-then rules obeying a level mapping and is thus free of circular justification, while the two minimality principles ensure that the formalism minimizes knowledge both at the level of answer sets and of world views. We thus propose to consider the three refined GAS principles as alternative principles for answer set semantics in general and for answer set and world view construction in particular. Third, to embody the refined GAS principles, we extend the notion of well-supportedness substantially to answer sets and world views, respectively. Fourth, we propose to define answer set semantics in terms of the refined GAS principles, called rational answer set and rational world view semantics, respectively. Fifth, we use the refined GAS principles as an alternative baseline to intuitively assess the existing answer set semantics whether they satisfy (are compliant with) or even fully embody the refined GAS principles. Finally, we analyze the computational complexity of well-supportedness and the rational answer set and world view semantics, revealing them as expressive hosts for problem solving.
- 13 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computational Logic
- Vol. 27 (4) , 1-72
Open AccessRefining Gelfond’s Rationality Principle: Towards More Comprehensive Foundational Principles for Answer Set Semantics
Non-monotonic logic programming is the basis for a declarative problem-solving paradigm known as answer set programming (ASP), where solutions to problems are encoded by intended models (answer sets) of a logic program. Departing from the seminal definition by Gelfond and Lifschitz for simple normal logic programs, various answer set semantics have been proposed for extensions such as disjunctive logic programs and epistemic logic programs. In the latter case, the semantics consists of sets of answer sets called world views. In general, it seems infeasible to formally prove whether a proposal defines answer sets/world views that correspond exactly to the solutions of any problem intuitively represented by a logic program. It is thus necessary to develop some general principles and use them as a baseline to intuitively compare and assess different answer set and world view semantics, respectively. Towards such a baseline, we consider two important questions: (1) Should the minimal model property, constraint monotonicity, and foundedness as defined in the literature be mandatory conditions for an answer set semantics in general? (2) If not, what other properties could be considered as alternative principles for answer set semantics? We address the two questions with several contributions. First, we use examples to demonstrate that requiring minimal models, constraint monotonicity, and foundedness as mandatory conditions may exclude expected answer sets for some simple disjunctive programs and world views for some epistemic specifications. Second, we evolve the Gelfond answer set (GAS) principles for answer set construction by refining Gelfond’s rationality principle to well-supportedness, minimality w.r.t. negation by default, and minimality w.r.t. epistemic negation. The principle of well-supportedness guarantees that every answer set is constructible from if-then rules obeying a level mapping and is thus free of circular justification, while the two minimality principles ensure that the formalism minimizes knowledge both at the level of answer sets and of world views. We thus propose to consider the three refined GAS principles as alternative principles for answer set semantics in general and for answer set and world view construction in particular. Third, to embody the refined GAS principles, we extend the notion of well-supportedness substantially to answer sets and world views, respectively. Fourth, we propose to define answer set semantics in terms of the refined GAS principles, called rational answer set and rational world view semantics, respectively. Fifth, we use the refined GAS principles as an alternative baseline to intuitively assess the existing answer set semantics whether they satisfy (are compliant with) or even fully embody the refined GAS principles. Finally, we analyze the computational complexity of well-supportedness and the rational answer set and world view semantics, revealing them as expressive hosts for problem solving.
- 11 October 2026
- Published by Springer Nature
- p. 215-230
Bayesian Hyperparameter Optimization with ALASPO
- 11 October 2026
- Published by Springer Nature
- p. 215-230
Bayesian Hyperparameter Optimization with ALASPO
- 11 October 2026
- Published by Springer Nature
- p. 67-82
On the Complexity of Model Checking for Temporal Equilibrium Logic
- 11 October 2026
- Published by Springer Nature
- p. 67-82
On the Complexity of Model Checking for Temporal Equilibrium Logic
- 11 October 2026
- Published by Springer Nature
- p. 150-166
Brief Temporal Equilibrium Logic
- 11 October 2026
- Published by Springer Nature
- p. 3-18
Emergency Planning for Norm Violations via ASP-Based Stream Reasoning
- 11 October 2026
- Published by Springer Nature
- p. 3-18
Emergency Planning for Norm Violations via ASP-Based Stream Reasoning
- Open Access
- 31 July 2026
- Published by Cambridge University Press (CUP) in Theory and Practice of Logic Programming
- p. 1-35
Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering
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. 1
- 31 July 2026
- Published by Cambridge University Press (CUP) in Theory and Practice of Logic Programming
- p. 1-35
Open AccessDistilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering
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. 1
- Open Access
- 24 March 2026
- Published by SAGE Publications in Neurosymbolic Artificial Intelligence
- Vol. 2
Leveraging Neurosymbolic AI for Slice Discovery
While remarkable recent developments in deep neural networks have significantly contributed to advancing the state-of-the-art in computer vision (CV), several studies have also shown their limitations and defects. In particular, CV models often make systematic errors on important subsets of data called slices , which are groups of data sharing a set of attributes. A slice discovery method (SDM) is meant to detect semantically meaningful slices on which the model performs poorly, called rare slices . We propose a modular neurosymbolic SDM whose distinctive advantage is the extraction via inductive logic programming of human-readable logical rules describing rare slices, and thus enhancing the explainability of CV models. To this end, a methodology for inducing the occurrence of rare slices in a model is presented. We validate the SDM approach on both the synthetic Super-CLEVR and real-world ImageNet datasets. Our experiments demonstrate the complete pipeline: first, we successfully induce targeted rare slices using our taxonomy-based heuristic; second, our neurosymbolic SDM correctly identifies these slices and produces precise, human-readable logical rules to describe them; and finally, these rules are used to guide a data augmentation process that successfully mends model behaviour and improves its predictive performance. 1
- 24 March 2026
- Published by SAGE Publications in Neurosymbolic Artificial Intelligence
- Vol. 2
Open AccessLeveraging Neurosymbolic AI for Slice Discovery
While remarkable recent developments in deep neural networks have significantly contributed to advancing the state-of-the-art in computer vision (CV), several studies have also shown their limitations and defects. In particular, CV models often make systematic errors on important subsets of data called slices , which are groups of data sharing a set of attributes. A slice discovery method (SDM) is meant to detect semantically meaningful slices on which the model performs poorly, called rare slices . We propose a modular neurosymbolic SDM whose distinctive advantage is the extraction via inductive logic programming of human-readable logical rules describing rare slices, and thus enhancing the explainability of CV models. To this end, a methodology for inducing the occurrence of rare slices in a model is presented. We validate the SDM approach on both the synthetic Super-CLEVR and real-world ImageNet datasets. Our experiments demonstrate the complete pipeline: first, we successfully induce targeted rare slices using our taxonomy-based heuristic; second, our neurosymbolic SDM correctly identifies these slices and produces precise, human-readable logical rules to describe them; and finally, these rules are used to guide a data augmentation process that successfully mends model behaviour and improves its predictive performance. 1
- Open Access
- 1 March 2026
- Published by Cambridge University Press (CUP) in Theory and Practice of Logic Programming
- Vol. 26 (1-2) , 46-63
Answer-Set-Programming-Based Abstractions for Reinforcement Learning
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 Prologue, CARCASS leverages domain knowledge to create powerful abstractions. We explore Answer-Set Programming (ASP), which is a rich and, contrary to Prologue, 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 (our implementation is available at https://github.com/rbankosegger/RLASP-core . Further material (data, encodings, extended documentation) can be found here: https://www.bankosegger.at/iclp26/ ).
- 1 March 2026
- Published by Cambridge University Press (CUP) in Theory and Practice of Logic Programming
- Vol. 26 (1-2) , 46-63
Open AccessAnswer-Set-Programming-Based Abstractions for Reinforcement Learning
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 Prologue, CARCASS leverages domain knowledge to create powerful abstractions. We explore Answer-Set Programming (ASP), which is a rich and, contrary to Prologue, 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 (our implementation is available at https://github.com/rbankosegger/RLASP-core . Further material (data, encodings, extended documentation) can be found here: https://www.bankosegger.at/iclp26/ ).
- Open Access
An XAI View on Explainable ASP: Methods, Systems, and Perspectives
Answer Set Programming (ASP) is a popular declarative reasoning and problem solving approach in symbolic AI. Its rule-based formalism makes it inherently attractive for explainable and interpretive reasoning, which is gaining importance with the surge of Explainable AI (XAI). A number of explanation approaches and tools for ASP have been developed, which often tackle specific explanatory settings and may not cover all scenarios that ASP users encounter. In this survey, we provide, guided by an XAI perspective, an overview of types of ASP explanations in connection with user questions for explanation, and describe how their coverage by current theory and tools. Furthermore, we pinpoint gaps in existing ASP explanations approaches and identify research directions for future work.
Open AccessAn XAI View on Explainable ASP: Methods, Systems, and Perspectives
Answer Set Programming (ASP) is a popular declarative reasoning and problem solving approach in symbolic AI. Its rule-based formalism makes it inherently attractive for explainable and interpretive reasoning, which is gaining importance with the surge of Explainable AI (XAI). A number of explanation approaches and tools for ASP have been developed, which often tackle specific explanatory settings and may not cover all scenarios that ASP users encounter. In this survey, we provide, guided by an XAI perspective, an overview of types of ASP explanations in connection with user questions for explanation, and describe how their coverage by current theory and tools. Furthermore, we pinpoint gaps in existing ASP explanations approaches and identify research directions for future work.
- Open Access
- 21 October 2025
- Published by IOS Press
- p. 3315-3322
OFTEN-DEEPRL: On-the-Fly Teaching of Ethical Norms to Deep Reinforcement Learning Agents
AI agents trained with reinforcement learning (RL) usually focus on completing their intended tasks without detours, as doing so typically maximizes their reward. However, real-world deployment requires agents that not only achieve their goals but also comply with ethical and societal norms that may conflict with their learned behavior. In this work, we present OFTEN-DEEPRL, an approach to integrate ethical norms into agents trained with deep reinforcement learning. The approach starts by training an RL policy focused on task performance. Building upon such a pre-trained policy, OFTEN-DEEPRL adapts the policy through norm-guided training. For a combination of observations and domain knowledge, we employ a logic program that generates norm-compliant plans for the agent using answer set programming (ASP) within a given planning horizon. These plans serve as demonstrations for fine-tuning the agent’s policy in the norm-guided training phase, guiding it toward behavior that remains effective while respecting the specified norms. We validate our approach with three types of scenarios: Pac-Man, a gardener simulation, and a SUMO-RL traffic control scenario. In all settings, agents fine-tuned with OFTEN-DEEPRL achieve comparable task performance while significantly reducing norm violations.
- 21 October 2025
- Published by IOS Press
- p. 3315-3322
Open AccessOFTEN-DEEPRL: On-the-Fly Teaching of Ethical Norms to Deep Reinforcement Learning Agents
AI agents trained with reinforcement learning (RL) usually focus on completing their intended tasks without detours, as doing so typically maximizes their reward. However, real-world deployment requires agents that not only achieve their goals but also comply with ethical and societal norms that may conflict with their learned behavior. In this work, we present OFTEN-DEEPRL, an approach to integrate ethical norms into agents trained with deep reinforcement learning. The approach starts by training an RL policy focused on task performance. Building upon such a pre-trained policy, OFTEN-DEEPRL adapts the policy through norm-guided training. For a combination of observations and domain knowledge, we employ a logic program that generates norm-compliant plans for the agent using answer set programming (ASP) within a given planning horizon. These plans serve as demonstrations for fine-tuning the agent’s policy in the norm-guided training phase, guiding it toward behavior that remains effective while respecting the specified norms. We validate our approach with three types of scenarios: Pac-Man, a gardener simulation, and a SUMO-RL traffic control scenario. In all settings, agents fine-tuned with OFTEN-DEEPRL achieve comparable task performance while significantly reducing norm violations.