Transcribing historical Arabic manuscripts into machine-readable text is essential for preserving cultural heritage and enabling computational research in the humanities, yet it remains a challenging task due to handwriting variability, page degradation, and the complexity of Arabic script. To advance research in this area, we introduce the NAKBA NLP 2026 shared task on Arabic manuscript understanding, comprising two complementary tracks: a manual transcription track, in which participating teams annotate unlabelled handwritten line images, and an automatic system track for handwritten text recognition (HTR). Both tracks use the Omar Al-Saleh Memoir Collection, a corpus of 6,395 scanned pages and approximately 1.6 million words, written between 1951 and 1965 and provided by the Palestine Memory Project. The dataset, evaluation scripts, and system outputs are publicly available.[https://acr.ps/1L9BaeY] In Subtask 1 (Transcription Track), three teams contributed manual line-level transcriptions; evaluation on hidden ground-truth samples yielded Character Error Rates (CER) between 0.06 and 0.11. In Subtask 2 (Systems Track), seven teams submitted HTR systems. The top-performing system, by Misraj AI, achieved a corpus-level CER of 0.079 and Word Error Rate (WER) of 0.244, outperforming the organiser baseline (CER 0.368, WER 0.691). Rankings shift between corpus-level and per-line evaluation: the 3reeq team achieved the lowest per-line CER (0.082). All contributed transcriptions and system outputs are released under CC-BY-4.0 to support continued research in Arabic manuscript recognition and digital humanities.

We present NeoAraBERT, a state-of-the-art open-source Arabic text-embedding model built on the NeoBERT architecture. We pre-train NeoAraBERT on diverse open-source and internal datasets covering modern standard, classical, and dialectal Arabic. We guided our design choices with Arabic tailored ablation studies including text normalization, light stemming, and diacritics-aware tokenization handling. We also performed more general POS-aware token masking and learning-rate scheduling ablation studies. We benchmarked NeoAraBERT against five top-performing Arabic models on 23 tasks, including a novel synonym-based task, “Muradif”, that directly assesses embedding quality with no additional fine-tuning. NeoAraBERT variants (MSA, dialectal, and mixed) rank first in 18 tasks, second in two, third in two, and fourth in one task. They show strong performance on classical and modern standard Arabic, substantial margins of improvement (>7%) in two tasks, and a +2.75% improvement on average across all tasks. Our code and links to checkpoints for our model variants are available on our website: https://acr.ps/neoarabert.

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.

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.

This paper details our submission to the WojoodNER Shared Task 2024, leveraging in-context learning with large language models for Arabic Named Entity Recognition. We utilized the Command R model, to perform fine-grained NER on the Wojood-Fine corpus. Our primary approach achieved an F1 score of 0.737 and a recall of 0.756. Post-processing the generated predictions to correct format inconsistencies resulted in an increased recall of 0.759, and a similar F1 score of 0.735. A multi-level prompting method and aggregation of outputs resulted in a lower F1 score of 0.637. Our results demonstrate the potential of ICL for Arabic NER while highlighting challenges related to LLM output consistency.

In this paper, we present our submission for the WojoodNER 2024 Shared Tasks addressing flat and nested sub-tasks (1, 2). We experiment with three different approaches. We train (i) an Arabic fine-tuned version of BLOOMZ-7b-mt, GEMMA-7b, and AraBERTv2 on multi-label token classifications task; (ii) two AraBERTv2 models, on main types and sub-types respectively; and (iii) one model for main types and four for the four sub-types. Based on the Wojood NER 2024 test set results, the three fine-tuned models performed similarly with AraBERTv2 favored (F1: Flat=.8780 Nested=.9040). The five model approach performed slightly better (F1: Flat=.8782 Nested=.9043).

The Differential Analysis Visualizer for Electronic Medical Records (DAVE) is a tool that utilizes natural language processing and machine learning to help visualize diagnostic algorithms in real-time to help support medical professionals in their clinical decision-making process