The growing collaboration between humans and AI models in generative tasks has introduced new challenges in distinguishing between human-written, LLM-generated, and human-LLM collaborative texts. In this work, we collect a multilingual, multi-domain, multi-generator dataset FAIDSet. We further introduce a fine-grained detection framework FAID to classify text into these three categories, and also to identify the underlying LLM family of the generator. Unlike existing binary classifiers, FAID is built to capture both authorship and model-specific characteristics. Our method combines multi-level contrastive learning with multi-task auxiliary classification to learn subtle stylistic cues. By modeling LLM families as distinct stylistic entities, we incorporate an adaptation to address distributional shifts without retraining for unseen data. Our experimental results demonstrate that FAID outperforms several baselines, particularly enhancing the generalization accuracy on unseen domains and new LLMs, thus offering a potential solution for improving transparency and accountability in AI-assisted writing. Our data and code are available at https://github.com/mbzuai-nlp/FAID

翻译：随着人类与AI模型在生成任务中的协作日益增多，区分人类撰写、大语言模型生成以及人机协作文本带来了新的挑战。本研究收集了一个多语言、多领域、多生成器的数据集FAIDSet。我们进一步提出了一个细粒度检测框架FAID，旨在将文本分类为上述三类，并识别生成文本的底层大语言模型家族。与现有的二分类器不同，FAID旨在捕捉作者身份和模型特异性特征。我们的方法结合了多层次对比学习与多任务辅助分类，以学习细微的风格线索。通过将不同的大语言模型家族建模为独特的风格实体，我们引入了一种适应机制，以应对分布偏移，而无需针对未见数据重新训练。实验结果表明，FAID在多个基线模型上表现更优，特别是在未见领域和新大语言模型上的泛化准确性显著提升，从而为增强AI辅助写作的透明度和可问责性提供了一个潜在的解决方案。我们的数据和代码公开于 https://github.com/mbzuai-nlp/FAID。