We present our approach to the AbjadGenEval shared task on detecting AI-generated Arabic text. We fine-tuned the multilingual E5-large encoder for binary classification, and we explored several pooling strategies to pool token representations, including weighted layer pooling, multi-head attention pooling, and gated fusion. Interestingly, none of these outperformed simple mean pooling, which achieved an F1 of 0.75 on the test set. We believe this is because complex pooling methods introduce additional parameters that need more data to train properly, whereas mean pooling offers a stable baseline that generalizes well even with limited examples. We also observe a clear pattern in the data: human-written texts tend to be significantly longer than machine-generated ones.
Figures & tables
Statistic
Human
Machine
Samples
2,649
2,649
Avg. Words
632.0
303.0
Avg. Characters
3,806.7
1,865.5
Max Words
3,068
1,969
Table 1: Dataset statistics by class. Human-written texts are significantly longer than machine-generated texts.
Parameter
Value
Model
multilingual-e5-large
Max Sequence Length
512 tokens
Batch Size
16
Gradient Accumulation
4 steps
Effective Batch Size
64
Learning Rate
2×10−5
Table 2: Training hyperparameters.
Pooling Strategy
Test F1
Mean Pooling
0.75
Weighted Layer Pooling + Attention
+ Gated Fusion
0.70
Weighted Layer Pooling + Attention
0.71
Table 3: Pooling strategy comparison on development set (2 samples). All methods achieved perfect dev scores, but mean pooling performed best on test.
Figure 1: Dataset analysis: (a) Balanced class distribution with 2,649 samples per class. (b) Word count distribution showing human texts are significantly longer.
This paper presents system description for Arabic medical text classification across 82 distinct categories. Our primary architecture utilizes a fine-tuned AraBERTv2 encoder enhanced with a hybrid pooling strategies, combining attention and mean representations, and multi-sample dropout for robust regularization. We systematically benchmark this approach against a suite of multilingual and Arabic-specific encoders, as well as several large-scale causal decoders, including zero-shot re-ranking via Llama 3.3 70B and feature extraction from Qwen 3B hidden states. Our findings demonstrate that specialized bidirectional encoders significantly outperform causal decoders in capturing the precise semantic boundaries required for fine-grained medical text classification. We show that causal decoders, optimized for next-token prediction, produce sequence-biased embeddings that are less effective for categorization compared to the global context captured by bidirectional attention. Despite significant class imbalance and label noise identified within the training data, our results highlight the superior semantic compression of fine-tuned encoders for specialized Arabic NLP tasks. Final performance metrics on the test set, including Accuracy and Macro-F1, are reported and discussed.
This paper describes the system submitted by team Archaeology to SemEval-2026 Task~13 on AI-generated code detection. The shared task consists of three subtasks; we participate in Subtask-A (binary classification: human-written vs.\ AI-generated code) and Subtask-B (11-class attribution of the generating model). Starting from a TF-IDF and Logistic Regression baseline, we fine-tune four pre-trained code models (CodeBERT, GraphCodeBERT, UniXcoder, and CodeT5+) with separate strategies for each subtask. For Subtask-A, we use leave-one-language-out cross-validation, code augmentation, chunked inference with trimmed-mean aggregation, and threshold calibration on a difficult dataset. For Subtask-B, we use sandwich token packing, class-balanced loss, and multi-seed ensembling with test-time augmentation. Our best submissions obtain macro-F1 scores of 0.737 on Subtask-A (6th/81 teams) and 0.422 on Subtask-B (7th/34 teams).
Jany-Gabriel Ispas, Sergiu Nisioi
Human Language Technologies Research Center Faculty of Mathematics and Computer Science University of Bucharest
With the rise of generative language models, machine-generated text detection has become a critical challenge. A wide variety of models is available, but inconsistent datasets, evaluation metrics, and assessment strategies obscure comparisons of model effectiveness. To address this, we evaluate 15 different detection models from six distinct systems, as well as seven trained models, across seven English-language textual test sets and three creative human-written datasets. We provide an empirical analysis of model performance, the influence of training and evaluation data, and the impact of key metrics. We find that no single system excels in all areas and nearly all are effective for certain tasks, and the representation of model performance is critically linked to dataset and metric choices. We find high variance in model ranks based on datasets and metrics, and overall poor performance on novel human-written texts in high-risk domains. Across datasets and metrics, we find that methodological choices that are often assumed or overlooked are essential for clearly and accurately reflecting model performance.