针对专业领域文本生成检测难题，提出无需训练的DivScore方法。
DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains
- 用归一化熵与领域知识蒸馏设计零样本检测框架
- 医学法律领域检测性能提升14.4% AUROC、64%召回率
- 适合需要高可靠性文本真伪验证的专业场景
在医疗、法律等高风险专业领域检测大模型生成文本对防止虚假信息至关重要。然而现有零样本检测器因领域偏移问题，在专业内容上表现不佳。我们通过理论分析指出其失败根源在于人类、检测器与源文本分布间的KL散度。为此提出DivScore：一种基于归一化熵评分与领域知识蒸馏的零样本检测框架，可有效识别专业领域中的生成文本。我们还发布了医疗与法律领域的专用检测基准。实验表明，DivScore在该基准上持续优于现有最优检测器，AUROC高出14.4%，在0.1%假阳性率阈值下召回率提升64.0%。对抗环境下，其平均在AUROC上领先22.8%，召回率领先29.5%。代码与数据已公开。
原文摘要 · Abstract (English)
Detecting LLM-generated text in specialized and high-stakes domains like medicine and law is crucial for combating misinformation and ensuring authenticity. However, current zero-shot detectors, while effective on general text, often fail when applied to specialized content due to domain shift. We provide a theoretical analysis showing this failure is fundamentally linked to the KL divergence between human, detector, and source text distributions. To address this, we propose DivScore, a zero-shot detection framework using normalized entropy-based scoring and domain knowledge distillation to robustly identify LLM-generated text in specialized domains. We also release a domain-specific benchmark for LLM-generated text detection in the medical and legal domains. Experiments on our benchmark show that DivScore consistently outperforms state-of-the-art detectors, with 14.4% higher AUROC and 64.0% higher recall (0.1% false positive rate threshold). In adversarial settings, DivScore demonstrates superior robustness than other baselines, achieving on average 22.8% advantage in AUROC and 29.5% in recall. Code and data are publicly available.
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。