KG: {(chop,canbedone with, knife), (knife, islocatedat, kitchen)}. As anexample, forboth (sleep, ./,

When solving tasks in the field of natural language processing, we sometimes need dictionary tools, such as lexicons, word form dictionaries or knowledge bases. However, the availability of dictionary data is insufficient in many languages, especially in the case of low resourced languages. In this article, we introduce a new conceptual dictionary for the Slovak language as the first linguistic tool of this kind. Since Slovak language is a language with limited linguistic resources and there are currently not available any machine-readable linguistic data sources with a sufficiently large volume of data, many tasks which require automated processing of Slovak text achieve weaker results compared to other languages and are almost impossible to solve.

We introduce GuessingGame, a protocol for evaluating large language models (LLMs) as strategic question-askers in open-ended, open-domain settings. A Guesser LLM identifies a hidden object by posing free-form questions to an Oracle without predefined choices or candidate lists. To measure question quality, we propose two information gain (IG) metrics: a Bayesian method that tracks belief updates over semantic concepts using LLM-scored relevance, and an entropy-based method that filters candidates via ConceptNet. Both metrics are model-agnostic and support post hoc analysis. Across 858 games with multiple models and prompting strategies, higher IG strongly predicts efficiency: a one-standard-deviation IG increase reduces expected game length by 43\%. Prompting constraints guided by IG, such as enforcing question diversity, enable weaker models to significantly improve performance. These results show that question-asking in LLMs is both measurable and improvable, and crucial for interactive reasoning.

--ConceptBot is a modular robotic planning framework that combines Large Language Models and Knowledge Graphs to generate feasible and risk-aware plans despite ambiguities in natural language instructions and correctly analyzing the objects present in the environment--challenges that typically arise from a lack of commonsense reasoning. T o do that, ConceptBot integrates (i) an Object Property Extraction (OPE) module that enriches scene understanding with semantic concepts from ConceptNet, (ii) a User Request Processing (URP) module that disambiguates and structures instructions, and (iii) a Planner that generates context-aware, feasible pick-and-place policies. In comparative evaluations against Google SayCan, ConceptBot achieved 100% success on explicit tasks, maintained 87% accuracy on implicit tasks (versus 31% for SayCan), reached 76% on risk-aware tasks (versus 15%), and outperformed SayCan in application-specific scenarios, including material classification (70% vs. 20%) and toxicity detection (86% vs. 36%). On SafeAgentBench, ConceptBot achieved an overall score of 80% (versus 46% for the next-best baseline). These results, validated in both simulation and laboratory experiments, demonstrate ConceptBot's ability to generalize without domain-specific training and to significantly improve the reliability of robotic policies in unstructured environments. Advances in recent decades in robotic core capabilities, i.e., perception, control, and manipulation, have increased demand for autonomous systems in fields ranging from manufacturing to healthcare, logistics to home care, etc. These capabilities are deeply interconnected with the planning phase [1], as successful planning depends on a robot's ability to perceive its environment accurately, execute precise control, and perform effective manipulation. Despite significant progress, planning in robotic systems continues to face challenges, particularly in unstructured environments [2]. A key element in achieving effective planning is task decomposition [3], which involves breaking complex objectives into smaller, manageable actions. This process is essential for simplifying execution and ensuring flexibility in diverse environments. Traditional task decomposition approaches, however, often rely on rigid, pre-programmed templates or static models, which struggle to adapt to unfamiliar or dynamic conditions [4]-[7]. Recently, advancements in Large Language Models (LLMs) have introduced a more dynamic alternative. LLMs enable robots to process natural language instructions, understand contextual nuances, and dynamically decompose tasks into actionable steps [8]-[10]. However, directly employing pre-trained LLMs often leads to non-executable or ineffective plans, as these models struggle to account for domain-specific constraints and real-world feasibility [11]- [13].

Contextualized embeddings based on large language models (LLMs) are available for various languages, but their coverage is often limited for lower resourced languages. Using LLMs for such languages is often difficult due to a high computational cost; not only during training, but also during inference. Static word embeddings are much more resource-efficient ("green"), and thus still provide value, particularly for very low-resource languages. There is, however, a notable lack of comprehensive repositories with such embeddings for diverse languages. To address this gap, we present GrEmLIn, a centralized repository of green, static baseline embeddings for 87 mid- and low-resource languages. We compute GrEmLIn embeddings with a novel method that enhances GloVe embeddings by integrating multilingual graph knowledge, which makes our static embeddings competitive with LLM representations, while being parameter-free at inference time. Our experiments demonstrate that GrEmLIn embeddings outperform state-of-the-art contextualized embeddings from E5 on the task of lexical similarity. They remain competitive in extrinsic evaluation tasks like sentiment analysis and natural language inference, with average performance gaps of just 5-10\% or less compared to state-of-the-art models, given a sufficient vocabulary overlap with the target task, and underperform only on topic classification. Our code and embeddings are publicly available at https://huggingface.co/DFKI.

Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framework that integrates Knowledge Distillation (KD) from Large Visual Language Models (LVLMs) and knowledge infusion to enhance the performance of toxicity detection in hateful memes. Our approach extracts sub-knowledge graphs from ConceptNet, a large-scale commonsense Knowledge Graph (KG) to be infused within a compact VLM framework. The relational context between toxic phrases in captions and memes, as well as visual concepts in memes enhance the model's reasoning capabilities. Experimental results from our study on two hate speech benchmark datasets demonstrate superior performance over the state-of-the-art baselines across AU-ROC, F1, and Recall with improvements of 1.1%, 7%, and 35%, respectively. Given the contextual complexity of the toxicity detection task, our approach showcases the significance of learning from both explicit (i.e. KG) as well as implicit (i.e. LVLMs) contextual cues incorporated through a hybrid neurosymbolic approach. This is crucial for real-world applications where accurate and scalable recognition of toxic content is critical for creating safer online environments.

In the rapidly evolving field of robotics, integration of commonsense knowledge (CSK) in AI systems is becoming highly crucial to enhance the decision-making capabilities of robots, especially in nextgeneration multipurpose environments. This paper presents Robo-CSK-Organizer, a pioneering system that employs CSK, via a classical knowledge base, to facilitate sophisticated task-based object organization helpful in multipurpose robots. Unlike systems relying solely on deep learning tools such as ChatGPT, our Robo-CSK-Organizer system stands out in various crucial aspects. This includes: (1) its ability to resolve ambiguities and maintain consistency in object placement; (2) its adaptability to diverse task-based classifications; and moreover, (3) its contributions to explainable AI (XAI), consequently helping to foster trust and human-robot collaboration. This system's efficacy is underlined by DETIC (DEtector with Image Classes), an advanced extension of Detectron2 for object identification; BLIP (Bootstrapping Language-Image Pre-training) for context discernment; and most vitally by the adaptation of ConceptNet, a well-grounded commonsense knowledge base for reasoning based on semantic as well as pragmatic knowledge. While we deploy ConceptNet to extract CSK, the process in Robo-CSK-Organizer is generic enough to be replicated with other state-of-the-art knowledge bases. Controlled experiments and real-world applications, synopsized in this paper, make Robo-CSK-Organizer demonstrate superior performance in placing objects in contextually relevant locations, highlighting its clear capacity for commonsense-guided decision-making closer to the thresholds of human cognition. Hence, Robo-CSK-Organizer makes valuable contributions to Robotics and AI.

In Explainable AI (XAI), counterfactual explanations (CEs) are a well-studied method to communicate feature relevance through contrastive reasoning of "what if" to explain AI models' predictions. However, they only focus on important (i.e., relevant) features and largely disregard less important (i.e., irrelevant) ones. Such irrelevant features can be crucial in many applications, especially when users need to ensure that an AI model's decisions are not affected or biased against specific attributes such as gender, race, religion, or political affiliation. To address this gap, the concept of alterfactual explanations (AEs) has been proposed. AEs explore an alternative reality of "no matter what", where irrelevant features are substituted with alternative features (e.g., "republicans" -> "democrats") within the same attribute (e.g., "politics") while maintaining a similar prediction output. This serves to validate whether AI model predictions are influenced by the specified attributes. Despite the promise of AEs, there is a lack of computational approaches to systematically generate them, particularly in the text domain, where creating AEs for AI text classifiers presents unique challenges. This paper addresses this challenge by formulating AE generation as an optimization problem and introducing MoMatterXAI, a novel algorithm that generates AEs for text classification tasks. Our approach achieves high fidelity of up to 95% while preserving context similarity of over 90% across multiple models and datasets. A human study further validates the effectiveness of AEs in explaining AI text classifiers to end users. All codes will be publicly available.