This paper describes our system for StanceEval 2026 Track 2, which requires predicting stance toward targets not seen during training. We explored fine-tuning different Arabic BERT encoder models, using class weighting techniques, incorporating auxiliary sentiment and sarcasm tasks in sequential and parallel multi-task setups, and focal and margin-based contrastive losses. We also tried zero-shot and few-shot prompting, self-consistency with escalation, LoRA fine-tuning, and an ensemble approach. Our best-performing submission on the official blind test set was a training-free few-shot prompting approach using Gemini 2.5 Flash with an extended prompt, achieving an F_avg2 of 87.41 and an F_avg3 of 76.94, and ranking 8th out of 13 teams. This result shows that a simpler, training-free prompting approach can generalize to unseen targets more effectively than fine-tuned and ensemble systems.

This paper addresses automatic readability assessment of Arabic documents. It compares classical readability formulae, fine-tuned Arabic encoders, zero-shot large language models and a Co-occurrence Graphs for Arabic Readability (CoGAR). CoGAR, interpretable and LLM-free, represents a document as a co-occurrence network over content lemmas and use topology features such as density, clustering, path length and degree entropy to predict readability. Evaluated on the BAREC corpus over five ordinal levels, the method reaches a quadratic weighted kappa (QWK) of 0.756, on par with a sparse 35B-parameter LLM and well above the surface formulas Flesch and OSMAN.

An ablation shows that the signal lies in the graph’s shape rather than size, and that alternative graphs based on relations between named-entity carry almost no readability difficulty signal. We further distill a frontier LLM (Gemini) into a small Arabic encoder (NeoAraBERT) by silver labelling 30k chunks, reaching 0.714 QWK. We show that stacking an LLM with CoGAR improves on the LLM alone, reaching QWK 0.839 with GPT-4.1 and 0.852 with the open-weight Qwen-35B, our best result. The two signals are complementary and the gain does not depend on a proprietary model. Finally, we analyze how eight methods including CoGAR distribute reading levels across seven Arabic text sources ranging from children books to expert research manuscripts showing how the methods align with intuitive difficulty.