小样本微调让检测模型跨领域更准
Detecting AI-Generated Texts in Cross-Domains
- 用自建数据集训练鲁棒基线模型，支持多领域文本识别
- 仅需少量标注数据即可在新领域实现高精度检测
- 适合需要跨领域部署的AI内容检测系统
现有大语言模型生成文本检测工具在新领域上性能下降。为此，我们构建了一个包含多种人类写作与不同大语言模型生成文本的语料库，并基于RoBERTa改进得到基准模型RoBERTa-Ranker。提出一种仅需少量标注数据即可在新领域微调的方法。实验表明，该领域感知模型在同域和跨域文本检测中均优于DetectGPT与GPTZero，无论生成文本来自不同领域或未用于训练的其他大语言模型。该方法使构建跨领域统一检测系统成为可能。
原文摘要 · Abstract (English)
Existing tools to detect text generated by a large language model (LLM) have met with certain success, but their performance can drop when dealing with texts in new domains. To tackle this issue, we train a ranking classifier called RoBERTa-Ranker, a modified version of RoBERTa, as a baseline model using a dataset we constructed that includes a wider variety of texts written by humans and generated by various LLMs. We then present a method to fine-tune RoBERTa-Ranker that requires only a small amount of labeled data in a new domain. Experiments show that this fine-tuned domain-aware model outperforms the popular DetectGPT and GPTZero on both in-domain and cross-domain texts, where AI-generated texts may either be in a different domain or generated by a different LLM not used to generate the training datasets. This approach makes it feasible and economical to build a single system to detect AI-generated texts across various domains.
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。