用多语言编码器检测阿拉伯语机器生成文本，均值池化效果最佳。
GATech at AbjadGenEval Shared Task: Multilingual Embeddings for Arabic Machine-Generated Text Classification
- 微调E5-large编码器，尝试多种池化策略
- 均值池化在测试集上达F1=0.75，最优
- 适合关注阿拉伯语生成内容检测的研究者
我们提出的方法用于在AbjadGenEval共享任务中检测阿拉伯语机器生成文本。通过微调多语言E5-large编码器进行二分类，探索了加权层池化、多头注意力池化和门控融合等多种池化策略。有趣的是，这些复杂方法均未优于简单的均值池化，在测试集上达到F1=0.75。我们认为，复杂池化引入额外参数，需更多数据训练，而均值池化作为稳定基线，即使样本有限也具有强泛化能力。此外，我们观察到明显规律：人工撰写文本显著长于机器生成文本。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。