Abstract
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.
Abstract (translated)
我们介绍了针对AbjadGenEval任务检测AI生成的阿拉伯文本的方法。我们将多语言E5-large编码器进行了微调，以进行二分类，并探索了多种池化策略来合并token表示，包括加权层池化、多头注意力池化和门控融合。有趣的是，在测试集上，没有一种复杂方法的表现超过简单的均值池化，后者达到了0.75的F1分数。我们相信这是因为复杂的池化方法引入了额外需要大量数据进行适当训练的参数，而均值池法则提供了一个稳健的基础模型，即使在少量示例的情况下也能很好地泛化。此外，我们在数据中观察到一个明显的模式：人工撰写的文章往往比机器生成的文章要长得多。
URL
https://arxiv.org/abs/2603.10007
