SEF-CLGC at SemEval-2026 Task 11: Logical Notation Impact on Language Model Performance

This paper revisits our pipeline called Syllogistic Evaluation Framework-Common Logic Grammar Construction (SEF-CLGC). We combine formal logical notations with Small Language Models (SLMs) to evaluate reasoning performance on the SemEval-2026 Task 11 Subtask 1: Disentangling Content and Formal Reasoning in Large Language Models. Our experiments show that by relying solely on SLMs, trained on a combination of natural and symbolic languages, our best model achieves a content score of 27.80% on the task while significantly lowering the content bias in reasoning.

Overcoming the Generalization Limits of SLM Finetuning for Shape-Based Extraction of Datatype and Object Properties

Small language models (SLMs) have shown promises for relation extraction (RE) when extracting RDF triples guided by SHACL shapes focused on common datatype properties. This paper investigates how SLMs handle both datatype and object properties for a complete RDF graph extraction. We show that the key bottleneck is related to long-tail distribution of rare properties. To solve this issue, we evaluate several strategies: stratified sampling, weighted loss, dataset scaling, and template-based synthetic data augmentation. We show that the best strategy to perform equally well over unbalanced target properties is to build a training set where the number of occurrences of each property exceeds a given threshold. To enable reproducibility, we publicly released our datasets, experimental results and code. Our findings offer practical guidance for training shape-aware SLMs and highlight promising directions for future work in semantic RE.

Eat your own KR: a KR-based approach to index Semantic Web Endpoints and Knowledge Graphs

Over the last decade, knowledge graphs have multiplied, grown, and evolved on the World Wide Web, and the advent of new standards, vocabularies, and application domains has accelerated this trend. IndeGx is a framework leveraging an extensible base of rules to index the content of KGs and the capacities of their SPARQL endpoints. In this article, we show how knowledge representation (KR) and reasoning methods and techniques can be used in a reflexive manner to index and characterize existing knowledge graphs (KG) with respect to their usage of KR methods and techniques. We extended IndeGx with a fully ontology-oriented modeling and processing approach to do so. Using SPARQL rules and an OWL RL ontology of the indexing domain, IndeGx can now build and reason over an index of the contents and characteristics of an open collection of public knowledge graphs. Our extension of the framework relies on a declarative representation of procedural knowledge and collaborative environments (e.g., GitHub) to provide an agile, customizable, and expressive KR approach for building and maintaining such an index of knowledge graphs in the wild. In doing so, we help anyone answer the question of what knowledge is out there in the world wild Semantic Web in general, and we also help our community monitor which KR research results are used in practice. In particular, this article provides a snapshot of the state of the Semantic Web regarding supported standard languages, ontology usage, and diverse quality evaluations by applying this method to a collection of over 300 open knowledge graph endpoints.