{"slug": "u4rasd-at-knowledgegrapheval-2026-ontology-constrained-encoder-and-llm-systems", "title": "U4RASD at KnowledgeGraphEval-2026: Ontology-Constrained Encoder and LLM Systems for Arabic Relation Extraction", "summary": "The U4RASD team's ensemble of Yehia-RE, Qwen-RE, and TypedPair achieved a micro-F1 score of 94.06 and ranked 1st in Subtask 2 of KnowledgeGraphEval 2026, the directed Arabic relation extraction task covering 40 relations plus no_relation. The team's encoder systems used typed entity markers with separate relation-existence and relation-classification heads, while its LLM systems fine-tuned Yehia and Qwen3.5 with QLoRA and ontology-constrained prediction. Yehia-RE (full-vocabulary) scored 92.98, the best encoder scored 92.69, and Qwen-RE scored 91.94, which the authors say highlights the importance of constrained prediction and complementary modeling approaches for Arabic relation extraction.", "body_md": "arXiv:2610.12742v1 Announce Type: new \nAbstract: This paper details our submission to KnowledgeGraphEval 2026 Subtask 2 on directed Arabic relation extraction. We explored encoder-based and large language model approaches for predicting one of 40 relations or no_relation from an Arabic sentence and a subject-object pair. Our encoder systems use typed entity markers and separate relation-existence and relation-classification heads, while our LLM systems fine-tune Yehia and Qwen3.5 with QLoRA and ontology-constrained prediction. Our best system, an ensemble of Yehia-RE, Qwen-RE, and TypedPair, achieved a micro-F1 score of 94.06 and ranked 1st in Subtask 2. Yehia-RE (full-vocabulary) achieved 92.98, while the best encoder and Qwen-RE achieved 92.69 and 91.94 respectively. Our results highlight the importance of constrained prediction and complementary modeling approaches for Arabic relation extraction.", "url": "https://wpnews.pro/news/u4rasd-at-knowledgegrapheval-2026-ontology-constrained-encoder-and-llm-systems", "canonical_source": "https://arxiv.org/abs/2610.12742", "published_at": "2026-10-12 04:00:00+00:00", "updated_at": "2026-10-12 04:42:07.288251+00:00", "lang": "en", "topics": ["natural-language-processing", "large-language-models", "ai-research", "machine-learning"], "entities": ["U4RASD", "KnowledgeGraphEval 2026", "Yehia-RE", "Qwen-RE", "TypedPair", "Qwen3.5", "Yehia", "QLoRA"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/u4rasd-at-knowledgegrapheval-2026-ontology-constrained-encoder-and-llm-systems", "markdown": "https://wpnews.pro/news/u4rasd-at-knowledgegrapheval-2026-ontology-constrained-encoder-and-llm-systems.md", "text": "https://wpnews.pro/news/u4rasd-at-knowledgegrapheval-2026-ontology-constrained-encoder-and-llm-systems.txt", "jsonld": "https://wpnews.pro/news/u4rasd-at-knowledgegrapheval-2026-ontology-constrained-encoder-and-llm-systems.jsonld"}}