# U4RASD at KnowledgeGraphEval-2026: Ontology-Constrained Encoder and LLM Systems for Arabic Relation Extraction

arXiv: https://arxiv.org/abs/2610.12742 · HTML: https://mlsanity.com/paper/2610.12742/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 11 of 11)

- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA](https://mlsanity.com/paper/2312.03732/) (2023)
- [Revisiting Relation Extraction in the era of Large Language Models](https://mlsanity.com/paper/2305.05003/) (2023)
- [An Improved Baseline for Sentence-level Relation Extraction](https://mlsanity.com/paper/2102.01373/) (2021)
- [ORCA: A Challenging Benchmark for Arabic Language Understanding](https://mlsanity.com/paper/2212.10758/) (2022)
- [Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors](https://mlsanity.com/paper/2305.11159/) (2023)
- [Wojood: Nested Arabic Named Entity Corpus and Recognition using BERT](https://mlsanity.com/paper/2205.09651/) (2022)
- [Arabic Fine-Grained Entity Recognition](https://mlsanity.com/paper/2310.17333/) (2023)
- [Konooz: Multi-domain Multi-dialect Corpus for Named Entity Recognition](https://mlsanity.com/paper/2506.12615/) (2025)
- [AraModernBERT: Transtokenized Initialization and Long-Context Encoder Modeling for Arabic](https://mlsanity.com/paper/2603.09982/) (2026)

## Abstract (arXiv)

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.