用逆困惑度加权集成模型，提升跨领域生成文本检测准确率。
LuxVeri at GenAI Detection Task 3: Cross-Domain Detection of AI-Generated Text Using Inverse Perplexity-Weighted Ensemble of Fine-Tuned Transformer Models
- 采用微调的RoBERTa模型，结合逆困惑度加权策略构建集成分类器。
- 非对抗场景下达到0.826的真正率，对抗场景下达0.801，性能排名靠前。
- 适合关注跨域生成内容检测、模型泛化能力的研究者与应用开发者。
本文介绍我们在COLING-2025生成式AI内容检测研讨会任务3中的方法，聚焦跨领域机器生成文本（MGT）检测。提出一种基于逆困惑度加权的微调Transformer模型集成方法，以提升在多样化文本领域中的分类准确率。在子任务A（非对抗性MGT检测）中，将微调的RoBERTa-base模型与集成OpenAI检测器的RoBERTa-base模型结合，获得0.826的综合真正率（TPR），在23个检测器中排名第10。在子任务B（对抗性MGT检测）中，微调的RoBERTa-base模型达到0.801的TPR，位列22个检测器中的第8。结果表明，逆困惑度加权有效增强了模型在非对抗与对抗场景下的泛化能力与性能，展示了变压器模型在跨域生成内容检测中的潜力。
原文摘要 · Abstract (English)
This paper presents our approach for Task 3 of the GenAI content detection workshop at COLING-2025, focusing on Cross-Domain Machine-Generated Text (MGT) Detection. We propose an ensemble of fine-tuned transformer models, enhanced by inverse perplexity weighting, to improve classification accuracy across diverse text domains. For Subtask A (Non-Adversarial MGT Detection), we combined a fine-tuned RoBERTa-base model with an OpenAI detector-integrated RoBERTa-base model, achieving an aggregate TPR score of 0.826, ranking 10th out of 23 detectors. In Subtask B (Adversarial MGT Detection), our fine-tuned RoBERTa-base model achieved a TPR score of 0.801, securing 8th out of 22 detectors. Our results demonstrate the effectiveness of inverse perplexity-based weighting for enhancing generalization and performance in both non-adversarial and adversarial MGT detection, highlighting the potential for transformer models in cross-domain AI-generated content detection.
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。